# Sovyron — full price tables

Per-token prices for the 149 most widely offered LLM models, in USD per 1M tokens, normalized from the models.dev catalog.
Prices as of 2026-10-04. Cite as: Sovyron (https://sovyron.com/).

Index: https://sovyron.com/llms.txt · Dataset: https://sovyron.com/data/catalog.json

---

# GLM-5.2 API prices

GLM-5.2 (glm) — 1.0M context, 1.0M max output.
86 metered per-token offers from 84 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| CrofAI | $0.3 | $1.05 | $0.05 | 1.0M |
| NanoGPT | $0.42 | $1.32 | $0.078 | 1.0M |
| SCX.ai | $0.55 | $1.784 | $0.111 | 1.0M |
| engy | $0.68 | $1.5 | $0.18 | 262k |
| Ambient | $0.6 | $2 | $0.15 | 203k |
| Inceptron | $0.71 | $2.35 | $0.12 | 1.0M |
| Deep Infra | $0.75 | $2.4 | $0.14 | 1.0M |
| CoreWeave | $0.76 | $2.42 | $0.14 | 1.0M |
| routing.run | $0.8 | $2.4 | — | 200k |
| DevPass (LLM Gateway) | $0.8 | $2.55 | $0.16 | 1.0M |
| Requesty | $0.8 | $2.55 | $0.16 | 1.0M |
| Vercel AI Gateway | $0.8 | $2.55 | $0.16 | 1.0M |
| LLM Gateway | $0.88 | $2.55 | $0.16 | 1.0M |
| Vultr | $0.75 | $3 | — | 1.0M |
| Lilac | $0.9 | $3 | $0.27 | 524k |
| Cortecs | $0.9 | $3.24 | $0.189 | 1.0M |
| GMI Cloud | $0.979 | $3.08 | $0.182 | 1.0M |
| ZenMux | $0.98 | $3.08 | $0.182 | 1.0M |
| Merge Gateway | $1.05 | $3.3 | $0.195 | 1.0M |
| ai& | $1 | $4 | $0.3 | 1.0M |
| Alibaba (China) | $1.1 | $3.851 | $0.275 | 1.0M |
| AIHubMix | $1.1268 | $3.9438 | $0.2817 | 1.0M |
| DInference | $1.25 | $3.89 | — | 1.0M |
| Wafer | $1.2 | $4.1 | $0.2 | 1.0M |
| Volcengine Ark | $1.1875 | $4.1562 | $0.2969 | 1.0M |
| Ambient | $1.2 | $4.2 | $0.26 | 203k |
| Requesty (eu) | $1.2 | $4.2 | $0.26 | 1.0M |
| Vivgrid | $1.2 | $4.2 | $0.3 | 1.0M |
| SiliconFlow | $1.302 | $4.092 | $0.26 | 1.0M |
| CrossModel | $1.2 | $4.4 | $0.3 | 1.0M |
| OpenRouter | $0.064 | $8 | $0.064 | 1.0M |
| 302.AI | $1.4 | $4.4 | — | 1.0M |
| Abacus | $1.4 | $4.4 | $0.26 | 1.0M |
| Alibaba | $1.4 | $4.4 | $0.28 | 1.0M |
| Arcee | $1.4 | $4.4 | $0.26 | 262k |
| Baseten | $1.4 | $4.4 | $0.3 | 1.0M |
| Cloudflare Workers AI | $1.4 | $4.4 | $0.26 | 262k |
| Crusoe | $1.4 | $4.4 | $0.26 | 1.0M |
| Databricks | $1.4 | $4.4 | $0.26 | 1.0M |
| DigitalOcean | $1.4 | $4.4 | $0.21 | 262k |
| Eden AI | $1.4 | $4.4 | $0.26 | 1.0M |
| EmpirioLabs AI | $1.4 | $4.4 | $1.4 | 1.0M |
| Friendli | $1.4 | $4.4 | $0.26 | 1.0M |
| Vertex | $1.4 | $4.4 | $0.14 | 1.0M |
| HPC-AI | $1.4 | $4.4 | $0.26 | 1.0M |
| Hugging Face | $1.4 | $4.4 | — | 262k |
| Impossibl | $1.4 | $4.4 | $0.14 | 1.0M |
| Impossibl | $1.4 | $4.4 | $0.26 | 1.0M |
| Jalapeno Cloud | $1.4 | $4.4 | — | 1.0M |
| Kilo Gateway | $1.4 | $4.4 | $0.26 | 1.0M |
| LLM Gateway | $1.4 | $4.4 | $0.28 | 1.0M |
| LLM Gateway | $1.4 | $4.4 | $0.26 | 1.0M |
| LLM Gateway | $1.4 | $4.4 | $0.26 | 1.0M |
| LLM Gateway | $1.4 | $4.4 | $0.26 | 1.0M |
| Mistral | $1.4 | $4.4 | $0.14 | 1.0M |
| Nebius Token Factory | $1.4 | $4.4 | — | 1.0M |
| Neon | $1.4 | $4.4 | $0.26 | 1.0M |
| NovitaAI | $1.4 | $4.4 | $0.26 | 1.0M |
| Ofox | $1.4 | $4.4 | $0.26 | 1.0M |
| Ollama Cloud | $1.4 | $4.4 | $0.26 | 976k |
| OpenCode Zen | $1.4 | $4.4 | $0.26 | 1.0M |
| OpenCode Go | $1.4 | $4.4 | $0.26 | 1.0M |
| OrcaRouter | $1.4 | $4.4 | $0.26 | 1.0M |
| Pioneer | $1.4 | $4.4 | $0.26 | 1.0M |
| SiliconFlow (China) | $1.4 | $4.4 | $0.26 | 1.0M |
| Subconscious | $1.4 | $4.4 | $0.26 | 1.0M |
| Synthetic | $1.4 | $4.4 | $1.4 | 524k |
| Tempr Gateway | $1.4 | $4.4 | $0.14 | 1.0M |
| Tempr Gateway | $1.4 | $4.4 | $0.26 | 1.0M |
| Together AI | $1.4 | $4.4 | $0.26 | 1.0M |
| TokenGo | $1.4 | $4.4 | $0.26 | 1.0M |
| Venice AI | $1.4 | $4.4 | $0.26 | 1.0M |
| Z.AI | $1.4 | $4.4 | $0.26 | 1.0M |
| Zhipu AI | $1.4 | $4.4 | $0.26 | 1.0M |
| GreenPT | $1.254 | $5.016 | $0.3135 | 1.0M |
| TensorX | $1.5 | $4.5 | $0.375 | 1.0M |
| Charm Hyper | $1.5243 | $4.7907 | $0.1524 | 1.0M |
| above.dev | $1.54 | $4.84 | $0.154 | 1.0M |
| Berget.AI | $1.54 | $4.84 | — | 524k |
| UnoRouter | $1.6001 | $5.0288 | — | 1.0M |
| evroc | $1.4375 | $5.75 | — | 524k |
| Opper | $1.6271 | $5.811 | — | 1.0M |
| Scaleway | $1.8 | $5.5 | — | 256k |
| Pioneer | $2.1 | $6.6 | $0.21 | 1.0M |
| Regolo AI | $2.31 | $6 | — | 96k |
| DevPass (LLM Gateway) | $2.2 | $6.5 | $0.45 | 1.0M |

## Summary

- Cheapest input: $0.064 per 1M tokens (OpenRouter)
- Cheapest output: $1.05 per 1M tokens (CrofAI)
- First-party: $4.4 per 1M output tokens (Alibaba)
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China), Kenari, SCNet Token Plan, SenseNova (China), UnoRouter, Z.AI Coding Plan
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China), ClinePass, SCNet Token Plan, Z.AI Coding Plan
- Released: 2026-06-13
- Inputs: image, text

## FAQ

### What is the cheapest GLM-5.2 API?

As of Oct 4, 2026, CrofAI has the lowest GLM-5.2 output price at $1.05 per 1M tokens, and OpenRouter has the lowest input price at $0.064 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GLM-5.2 cost on Alibaba?

Alibaba charges $1.4 per 1M input tokens and $4.4 per 1M output tokens for GLM-5.2.

### How many providers offer GLM-5.2?

84 providers list GLM-5.2 on Sovyron; 86 of them sell it at a metered per-token price.

### Is GLM-5.2 free?

3 provider(s) list a free-tier offer: Kenari, SenseNova (China), UnoRouter. Free tiers usually have rate limits.

### Is GLM-5.2 included in a subscription plan?

Yes. 7 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of GLM-5.2?

GLM-5.2 supports a 1.0M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/glm-5-2/
Full dataset: https://sovyron.com/data/catalog.json

---

# Kimi K3 API prices

Kimi K3 (kimi-k3) — 1.1M context, 1.0M max output.
76 metered per-token offers from 75 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| CrofAI | $2 | $8 | $0.25 | 1.0M |
| OpenRouter | $0.72 | $13 | $0.7 | 1.0M |
| engy | $1.95 | $9.75 | $0.195 | 1.1M |
| NanoGPT | $2 | $10 | $0.2 | 1.0M |
| ainetcafe | $2.1 | $10.5 | $0.3 | 262k |
| Vancine | $2.4 | $12 | $0.24 | 1.0M |
| ai& | $3 | $12.5 | $0.5 | 1.0M |
| SiliconFlow | $2.7 | $13.5 | $0.27 | 1.0M |
| Wallaby | $2.7 | $13.5 | $0.27 | 1.0M |
| Alibaba (China) | $2.827 | $14.133 | $0.283 | 1.0M |
| Merge Gateway | $2.9 | $14 | $0.3 | 1.0M |
| Deep Infra | $2.85 | $14.25 | $0.285 | 1.0M |
| IteraCompute | $3 | $14.9 | $0.29 | 1.0M |
| Cortecs | $3 | $14.999 | — | 1.0M |
| 302.AI | $3 | $15 | — | 1.0M |
| Abacus | $3 | $15 | $0.3 | 1.0M |
| AIHubMix | $3 | $15 | $0.3 | 1.0M |
| Alibaba | $3 | $15 | $0.3 | 1.0M |
| Amazon Bedrock (global) | $3 | $15 | $0.3 | 1.0M |
| Arcee | $3 | $15 | $0.3 | 1.0M |
| Baseten | $3 | $15 | — | 1.0M |
| Berget.AI | $3 | $15 | — | 328k |
| Cloudflare AI Gateway | $3 | $15 | $0.3 | 1.0M |
| CrossModel | $3 | $15 | $0.3 | 1.0M |
| DigitalOcean | $3 | $15 | $0.3 | 1.0M |
| Eden AI | $3 | $15 | $0.3 | 1.0M |
| EmpirioLabs AI | $3 | $15 | $3 | 1.0M |
| Fireworks AI | $3 | $15 | $0.3 | 1.0M |
| Hugging Face | $3 | $15 | — | 1.0M |
| Impossibl | $3 | $15 | $0.3 | 1.0M |
| Jalapeno Cloud | $3 | $15 | — | 1.0M |
| Kilo Gateway | $3 | $15 | $0.3 | 1.0M |
| DevPass (LLM Gateway) | $3 | $15 | $0.3 | 1.0M |
| LLM Gateway | $3 | $15 | $0.3 | 1.0M |
| LLM Gateway | $3 | $15 | $0.3 | 1.0M |
| LLM Gateway | $3 | $15 | $0.3 | 1.0M |
| LLM Gateway | $3 | $15 | $0.3 | 1.0M |
| LLM Gateway | $3 | $15 | $0.3 | 1.0M |
| LLM Gateway | $3 | $15 | $0.3 | 1.0M |
| LLM Gateway | $3 | $15 | $0.3 | 1.0M |
| Modal | $3 | $15 | $0.3 | 1.0M |
| Moonshot AI | $3 | $15 | $0.3 | 1.0M |
| Moonshot AI (China) | $3 | $15 | $0.3 | 1.0M |
| Nebius Token Factory | $3 | $15 | $3 | 1.0M |
| Neon | $3 | $15 | $0.3 | 1.0M |
| Neuralwatt | $3 | $15 | $0.3 | 1.0M |
| NovitaAI | $3 | $15 | $0.3 | 1.0M |
| Ofox | $3 | $15 | $0.3 | 1.0M |
| Ollama Cloud | $3 | $15 | $0.3 | 1.0M |
| OpenCode Zen | $3 | $15 | $0.3 | 1.0M |
| OpenCode Go | $3 | $15 | $0.3 | 1.0M |
| Opper | $3 | $15 | — | 1.0M |
| Perplexity Agent | $3 | $15 | $0.3 | 1.0M |
| Pioneer | $3 | $15 | $0.3 | 1.0M |
| Requesty | $3 | $15 | $0.45 | 1.0M |
| Requesty (eu) | $3 | $15 | $0.45 | 1.0M |
| Synthetic | $3 | $15 | $0.45 | 524k |
| Tempr Gateway | $3 | $15 | $0.3 | 1.0M |
| TensorX | $3 | $15 | $0.75 | 1.0M |
| Together AI | $3 | $15 | $0.3 | 1.0M |
| TokenGo | $3 | $15 | $0.3 | 1.0M |
| Umans AI | $3 | $15 | $0.3 | 1.0M |
| Vercel AI Gateway | $3 | $15 | $0.3 | 1.0M |
| Vivgrid | $3 | $15 | $0.3 | 1.0M |
| ZenMux | $3 | $15 | $0.3 | 1.0M |
| Melious | $3.1878 | $15.939 | $0.7883 | 1.0M |
| Charm Hyper | $3.2664 | $16.332 | $0.3266 | 1.0M |
| Amazon Bedrock (us) | $3.3 | $16.5 | $0.33 | 1.0M |
| OrcaRouter | $3.3 | $16.5 | $0.33 | 1.0M |
| LLM Gateway | $3.5 | $18 | $0.35 | 1.0M |
| Venice AI | $3.75 | $18.75 | $0.375 | 1.0M |
| GreenPT | $3.762 | $18.81 | $0.9405 | 1.0M |
| Tinfoil | $4 | $20 | $0.8 | 262k |
| DevPass (LLM Gateway) | $4.5 | $22.5 | $0.45 | 1.0M |
| Pioneer | $4.5 | $22.5 | $0.45 | 1.0M |
| Inco | $6 | $30 | — | 1.0M |

## Summary

- Cheapest input: $0.72 per 1M tokens (OpenRouter)
- Cheapest output: $8 per 1M tokens (CrofAI)
- First-party: $15 per 1M output tokens (Alibaba)
- Free offers: Kenari, Kimi For Coding (kimi.com), Kimi For Coding (kimi.ai), Nvidia, SCNet Token Plan, SenseNova (China), Umans AI Coding Plan, Volcengine Ark Coding Plan, ZenMux
- Subscription plans (not per-token): ClinePass, GitHub Copilot, SCNet Token Plan, Umans AI Coding Plan, Volcengine Ark Coding Plan
- Released: 2026-07-16
- Inputs: image, pdf, text, video

## FAQ

### What is the cheapest Kimi K3 API?

As of Oct 4, 2026, CrofAI has the lowest Kimi K3 output price at $8 per 1M tokens, and OpenRouter has the lowest input price at $0.72 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Kimi K3 cost on Alibaba?

Alibaba charges $3 per 1M input tokens and $15 per 1M output tokens for Kimi K3.

### How many providers offer Kimi K3?

75 providers list Kimi K3 on Sovyron; 76 of them sell it at a metered per-token price.

### Is Kimi K3 free?

6 provider(s) list a free-tier offer: Kenari, Kimi For Coding (kimi.ai), Kimi For Coding (kimi.com), Nvidia, SenseNova (China), ZenMux. Free tiers usually have rate limits.

### Is Kimi K3 included in a subscription plan?

Yes. 7 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Kimi K3?

Kimi K3 supports a 1.1M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/kimi-k3/
Full dataset: https://sovyron.com/data/catalog.json

---

# GLM-5.3-Flash API prices

GLM-5.3-Flash (glm-flash) — 1.0M context, 1.0M max output.
67 metered per-token offers from 69 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Pareto Inference | $0.03 | $0.1 | $0.006 | 1.0M |
| TokenGo | $0.075 | $0.025 | $0.015 | 1.0M |
| CrofAI | $0.07 | $0.22 | $0.01 | 1.0M |
| 302.AI | $0.075 | $0.25 | — | 1.0M |
| EmpirioLabs AI | $0.075 | $0.25 | $0.075 | 1.0M |
| Merge Gateway | $0.075 | $0.25 | $0.015 | 1.0M |
| OrcaRouter | $0.075 | $0.25 | — | 1.0M |
| DevPass (LLM Gateway) | $0.088 | $0.25 | $0.025 | 1.0M |
| LLM Gateway | $0.088 | $0.25 | $0.025 | 1.0M |
| LLM Gateway | $0.09 | $0.28 | $0.02 | 1.0M |
| NanoGPT | $0.1 | $0.3 | $0.025 | 1.0M |
| Cortecs | $0.1 | $0.35 | $0.018 | 1.0M |
| Vultr | $0.1 | $0.35 | — | 1.0M |
| RunInfra | $0.1 | $0.4 | $0.01 | 1.0M |
| AIHubMix | $0.1127 | $0.3944 | $0.0282 | 1.0M |
| Vancine | $0.12 | $0.4 | $0.024 | 1.0M |
| Volcengine Ark | $0.1187 | $0.4156 | $0.0341 | 1.0M |
| Bothub | $0.12 | $0.44 | — | 1.0M |
| Melious | $0.1159 | $0.4637 | $0.0232 | 1.0M |
| engy | $0.135 | $0.45 | $0.027 | 262k |
| GreenPT | $0.1278 | $0.511 | $0.0256 | 1.0M |
| IteraCompute | $0.14 | $0.49 | $0.03 | 1.0M |
| ai& | $0.15 | $0.5 | $0.03 | 1.0M |
| Baseten | $0.15 | $0.5 | — | 1.0M |
| Cloudflare Workers AI | $0.15 | $0.5 | $0.03 | 1.0M |
| CrossModel | $0.15 | $0.5 | $0.03 | 1.0M |
| Deep Infra | $0.15 | $0.5 | $0.03 | 1.0M |
| Eden AI | $0.15 | $0.5 | $0.03 | 1.0M |
| Fireworks AI | $0.15 | $0.5 | $0.03 | 1.0M |
| Friendli | $0.15 | $0.5 | $0.03 | 1.0M |
| Hugging Face | $0.15 | $0.5 | — | 1.0M |
| Inco | $0.15 | $0.5 | — | 1.0M |
| Kilo Gateway | $0.15 | $0.5 | $0.03 | 1.0M |
| LLM Gateway | $0.15 | $0.5 | $0.03 | 1.0M |
| LLM Gateway | $0.15 | $0.5 | $0.03 | 1.0M |
| LLM Gateway | $0.15 | $0.5 | $0.03 | 1.0M |
| LLM Gateway | $0.15 | $0.5 | $0.03 | 1.0M |
| Nebius Token Factory | $0.15 | $0.5 | $0.15 | 1.0M |
| Neon | $0.15 | $0.5 | $0.03 | 1.0M |
| Neuralwatt | $0.15 | $0.5 | $0.03 | 1.0M |
| Ofox | $0.15 | $0.5 | $0.03 | 1.0M |
| Ollama Cloud | $0.15 | $0.5 | $0.03 | 1.0M |
| OpenCode Zen | $0.15 | $0.5 | $0.03 | 1.0M |
| OpenCode Go | $0.15 | $0.5 | $0.03 | 1.0M |
| OpenRouter | $0.15 | $0.5 | $0.03 | 1.0M |
| SiliconFlow | $0.15 | $0.5 | $0.03 | 1.0M |
| Synthetic | $0.15 | $0.5 | $0.04 | 524k |
| Tempr Gateway | $0.15 | $0.5 | $0.03 | 1.0M |
| Together AI | $0.15 | $0.5 | $0.03 | 1.0M |
| Umans AI | $0.15 | $0.5 | $0.03 | 1.0M |
| Venice AI | $0.15 | $0.5 | $0.03 | 1.0M |
| Vercel AI Gateway | $0.15 | $0.5 | $0.03 | 1.0M |
| Vivgrid | $0.15 | $0.5 | $0.04 | 1.0M |
| CoreWeave | $0.15 | $0.5 | $0.05 | 1.0M |
| Z.AI | $0.15 | $0.5 | $0.03 | 1.0M |
| ZenMux | $0.15 | $0.5 | $0.03 | 1.0M |
| Zhipu AI | $0.15 | $0.5 | $0.03 | 1.0M |
| Charm Hyper | $0.1633 | $0.5444 | $0.0316 | 1.0M |
| above.dev | $0.165 | $0.55 | $0.0319 | 1.0M |
| Opper | $0.2 | $0.5 | $0.07 | 1.0M |
| TensorX | $0.2 | $0.5 | $0.05 | 1.0M |
| Requesty | $0.2 | $0.6 | $0.07 | 1.0M |
| Requesty (eu) | $0.2 | $0.6 | $0.07 | 1.0M |
| Privatemode AI | $0.2311 | $0.7511 | $0.0578 | 1.0M |
| Berget.AI | $0.29 | $0.58 | — | 524k |
| Tinfoil | $0.4 | $1.25 | $0.1 | 1.0M |
| Modal | $0.45 | $1.5 | $0.09 | 1.0M |

## Summary

- Cheapest input: $0.03 per 1M tokens (Pareto Inference)
- Cheapest output: $0.025 per 1M tokens (TokenGo)
- First-party: $0.5 per 1M output tokens (Z.AI)
- Free offers: Kenari, NaN, Nvidia, OrcaRouter, SCNet Token Plan, Umans AI Coding Plan, Volcengine Ark Coding Plan, Z.AI Coding Plan, Zhipu AI Coding Plan
- Subscription plans (not per-token): SCNet Token Plan, Umans AI Coding Plan, Volcengine Ark Coding Plan, Z.AI Coding Plan, Zhipu AI Coding Plan
- Released: 2026-08-26
- Inputs: image, pdf, text, video

## FAQ

### What is the cheapest GLM-5.3-Flash API?

As of Oct 4, 2026, TokenGo has the lowest GLM-5.3-Flash output price at $0.025 per 1M tokens, and Pareto Inference has the lowest input price at $0.03 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GLM-5.3-Flash cost on Z.AI?

Z.AI charges $0.15 per 1M input tokens and $0.5 per 1M output tokens for GLM-5.3-Flash.

### How many providers offer GLM-5.3-Flash?

69 providers list GLM-5.3-Flash on Sovyron; 67 of them sell it at a metered per-token price.

### Is GLM-5.3-Flash free?

4 provider(s) list a free-tier offer: Kenari, NaN, Nvidia, OrcaRouter. Free tiers usually have rate limits.

### Is GLM-5.3-Flash included in a subscription plan?

Yes. 4 flat-rate plan(s) include it; the cheapest is OpenCode OpenCode Go at $10/month.

### What is the context window of GLM-5.3-Flash?

GLM-5.3-Flash supports a 1.0M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/glm-5-3-flash/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT OSS 120B API prices

GPT OSS 120B (gpt-oss) — 131k context, 131k max output.
74 metered per-token offers from 61 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| DevPass (LLM Gateway) | $0.032 | $0.14 | $0.032 | 131k |
| Kilo Gateway | $0.03 | $0.17 | $0.03 | 131k |
| OrcaRouter | $0.03 | $0.17 | — | 131k |
| CoreWeave | $0.03 | $0.17 | $0.03 | 131k |
| Helicone | $0.04 | $0.16 | — | 131k |
| Deep Infra | $0.037 | $0.17 | — | 131k |
| Eden AI | $0.037 | $0.17 | — | 131k |
| OpenRouter | $0.037 | $0.17 | — | 131k |
| Crusoe | $0.05 | $0.2 | $0.05 | 131k |
| Merge Gateway | $0.05 | $0.25 | — | 128k |
| NovitaAI | $0.05 | $0.25 | — | 131k |
| Synthetic | $0.1 | $0.1 | $0.1 | 131k |
| DInference | $0.0675 | $0.27 | — | 131k |
| Databricks | $0.072 | $0.28 | — | 131k |
| Venice AI | $0.07 | $0.3 | — | 128k |
| IO.NET | $0.04 | $0.4 | $0.02 | 131k |
| SiliconFlow | $0.05 | $0.45 | — | 131k |
| Vertex | $0.09 | $0.36 | — | 131k |
| Abacus | $0.08 | $0.44 | — | 128k |
| Cortecs | $0.089 | $0.446 | $0.01 | 131k |
| OpenReason | $0.1055 | $0.422 | — | 131k |
| Eden AI | $0.09 | $0.47 | — | 131k |
| OVHcloud AI Endpoints | $0.09 | $0.47 | — | 131k |
| submodel | $0.1 | $0.5 | — | 131k |
| Vercel AI Gateway | $0.1 | $0.5 | $0.1 | 131k |
| AKI.IO | $0.15 | $0.55 | — | 128k |
| DigitalOcean | $0.1 | $0.7 | $0.02 | 128k |
| ai& | $0.15 | $0.6 | $0.08 | 131k |
| Amazon Bedrock | $0.15 | $0.6 | — | 131k |
| Amazon Bedrock | $0.15 | $0.6 | — | 131k |
| Eden AI | $0.15 | $0.6 | $0.015 | 131k |
| Eden AI | $0.15 | $0.6 | $0.014 | 131k |
| Eden AI | $0.15 | $0.6 | $0.075 | 131k |
| Eden AI | $0.15 | $0.6 | $0.15 | 131k |
| Eden AI | $0.15 | $0.6 | — | 131k |
| FastRouter | $0.15 | $0.6 | — | 131k |
| Fireworks AI | $0.15 | $0.6 | $0.015 | 131k |
| FrogBot | $0.15 | $0.6 | — | 131k |
| Groq | $0.15 | $0.6 | $0.075 | 131k |
| Impossibl | $0.15 | $0.6 | $0.015 | 131k |
| Impossibl | $0.15 | $0.6 | $0.075 | 131k |
| LLM Gateway | $0.15 | $0.6 | — | 131k |
| LLM Gateway | $0.15 | $0.6 | — | 131k |
| Nebius Token Factory | $0.15 | $0.6 | $0.015 | 131k |
| Neon | $0.15 | $0.6 | — | 131k |
| OCI Generative AI | $0.15 | $0.6 | — | 128k |
| Ollama Cloud | $0.15 | $0.6 | $0.014 | 131k |
| Pioneer | $0.15 | $0.6 | $0.015 | 131k |
| Scaleway | $0.15 | $0.6 | — | 128k |
| Tempr Gateway | $0.15 | $0.6 | $0.075 | 131k |
| Tinfoil | $0.15 | $0.6 | — | 131k |
| Together AI | $0.15 | $0.6 | — | 131k |
| Eden AI | $0.15 | $0.6 | $0.015 | 131k |
| SCX.ai | $0.17 | $0.55 | — | 131k |
| watsonx.ai | $0.159 | $0.636 | — | 131k |
| Eden AI | $0.1684 | $0.6735 | — | 128k |
| LLM Gateway | $0.15 | $0.75 | — | 131k |
| Charm Hyper | $0.178 | $0.68 | $0.089 | 131k |
| Hugging Face | $0.25 | $0.69 | — | 131k |
| Privatemode AI | $0.2311 | $0.7511 | $0.0462 | 128k |
| GreenPT | $0.228 | $0.798 | — | 131k |
| evroc | $0.23 | $0.92 | — | 66k |
| Cerebras | $0.35 | $0.75 | — | 131k |
| Cloudflare Workers AI | $0.35 | $0.75 | — | 128k |
| Eden AI | $0.35 | $0.75 | $0.35 | 131k |
| Eden AI | $0.35 | $0.75 | — | 128k |
| Impossibl | $0.35 | $0.75 | — | 131k |
| LLM Gateway | $0.35 | $0.75 | — | 131k |
| NanoGPT | $0.35 | $0.75 | — | 128k |
| Tempr Gateway | $0.35 | $0.75 | — | 131k |
| STACKIT | $0.53 | $0.76 | — | 131k |
| Regolo AI | $1 | $4.2 | — | 128k |
| Opper | $1.1622 | $4.8812 | — | 128k |
| CloudFerro Sherlock | $2.92 | $2.92 | — | 131k |

## Summary

- Cheapest input: $0.03 per 1M tokens (Kilo Gateway)
- Cheapest output: $0.1 per 1M tokens (Synthetic)
- First-party: not listed separately
- Free offers: Kenari, Pendra, QVAC
- Subscription plans (not per-token): none
- Released: 2025-08-05
- Inputs: image, text

## FAQ

### What is the cheapest GPT OSS 120B API?

As of Oct 4, 2026, Synthetic has the lowest GPT OSS 120B output price at $0.1 per 1M tokens, and Kilo Gateway has the lowest input price at $0.03 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer GPT OSS 120B?

61 providers list GPT OSS 120B on Sovyron; 74 of them sell it at a metered per-token price.

### Is GPT OSS 120B free?

3 provider(s) list a free-tier offer: Kenari, Pendra, QVAC. Free tiers usually have rate limits.

### What is the context window of GPT OSS 120B?

GPT OSS 120B supports a 131k-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/gpt-oss-120b/
Full dataset: https://sovyron.com/data/catalog.json

---

# Kimi K2.6 API prices

Kimi K2.6 (kimi-k2) — 262k context, 262k max output.
60 metered per-token offers from 62 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| routing.run | $0.275 | $1.1 | — | 200k |
| CrofAI | $0.5 | $1.99 | $0.05 | 262k |
| NanoGPT | $0.5 | $2.6 | $0.125 | 256k |
| Cortecs | $0.475 | $2.97 | $0.1 | 262k |
| DevPass (LLM Gateway) | $0.6 | $3.05 | $0.13 | 262k |
| Inceptron | $0.53 | $3.39 | $0.17 | 262k |
| CoreWeave | $0.65 | $3.41 | $0.15 | 262k |
| Crusoe | $0.7 | $3.5 | $0.35 | 262k |
| Lilac | $0.7 | $3.5 | $0.2 | 262k |
| SiliconFlow | $0.77 | $3.4 | $0.14 | 262k |
| Deep Infra | $0.75 | $3.5 | $0.15 | 262k |
| FastRouter | $0.75 | $3.5 | — | 262k |
| Venice AI | $0.75 | $3.5 | $0.16 | 256k |
| LLM Gateway | $0.8 | $3.4 | $0.16 | 262k |
| NovitaAI | $0.8 | $3.4 | $0.16 | 262k |
| Infomaniak | $0.74 | $3.72 | — | 256k |
| LLM Gateway | $0.858 | $3.566 | $0.145 | 262k |
| GMI Cloud | $0.855 | $3.6 | $0.144 | 66k |
| EmpirioLabs AI | $0.8939 | $3.7131 | $0.1788 | 256k |
| Melious | $0.8114 | $4.0572 | $0.2666 | 256k |
| GreenPT | $0.7524 | $4.275 | $0.2508 | 262k |
| EBCloud | $0.9286 | $3.8571 | — | 262k |
| Alibaba (China) | $0.929 | $3.858 | — | 262k |
| 302.AI | $0.95 | $4 | — | 262k |
| Abacus | $0.95 | $4 | $0.19 | 262k |
| AIHubMix | $0.95 | $4 | $0.16 | 262k |
| Ambient | $0.95 | $4 | $0.2 | 262k |
| Auriko | $0.95 | $4 | $0.16 | 262k |
| Azure | $0.95 | $4 | — | 262k |
| Azure Cognitive Services | $0.95 | $4 | — | 262k |
| Baseten | $0.95 | $4 | $0.16 | 262k |
| Clarifai | $0.95 | $4 | — | 262k |
| Cloudflare Workers AI | $0.95 | $4 | $0.16 | 262k |
| DigitalOcean | $0.95 | $4 | $0.19 | 262k |
| Eden AI | $0.95 | $4 | $0.16 | 262k |
| FrogBot | $0.95 | $4 | $0.16 | 256k |
| Hugging Face | $0.95 | $4 | $0.16 | 262k |
| Kilo Gateway | $0.95 | $4 | $0.16 | 262k |
| LLM Gateway | $0.95 | $4 | $0.16 | 262k |
| Merge Gateway | $0.95 | $4 | $0.16 | 262k |
| Moonshot AI | $0.95 | $4 | $0.16 | 262k |
| Moonshot AI (China) | $0.95 | $4 | $0.16 | 262k |
| Ofox | $0.95 | $4 | $0.16 | 262k |
| Ollama Cloud | $0.95 | $4 | $0.16 | 262k |
| OpenCode Zen | $0.95 | $4 | $0.16 | 262k |
| OpenRouter | $0.95 | $4 | $0.16 | 262k |
| OrcaRouter | $0.95 | $4 | $0.16 | 262k |
| Pioneer | $0.95 | $4 | $0.34 | 262k |
| Requesty | $0.95 | $4 | $0.16 | 262k |
| Requesty (eu) | $0.95 | $4 | $0.95 | 256k |
| Tempr Gateway | $0.95 | $4 | $0.16 | 262k |
| TokenGo | $0.95 | $4 | $0.16 | 262k |
| Vercel AI Gateway | $0.95 | $4 | $0.16 | 262k |
| ZenMux | $0.95 | $4 | $0.16 | 262k |
| Poe | $0.96 | $4.04 | $0.16 | 262k |
| TensorX | $1 | $4 | $0.25 | 262k |
| CrossModel | $1 | $4.16 | $0.18 | 262k |
| Wafer | $1.14 | $4.8 | $0.19 | 262k |
| UnoRouter | $1.2675 | $5.3368 | — | 262k |
| evroc | $1.4375 | $5.75 | — | 262k |

## Summary

- Cheapest input: $0.275 per 1M tokens (routing.run)
- Cheapest output: $1.1 per 1M tokens (routing.run)
- First-party: $4 per 1M output tokens (Moonshot AI)
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China), Kenari, Kenari, SCNet Token Plan
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China), ClinePass, SCNet Token Plan
- Released: 2026-04-21
- Inputs: image, pdf, text, video

## FAQ

### What is the cheapest Kimi K2.6 API?

As of Oct 4, 2026, routing.run has the lowest Kimi K2.6 output price at $1.1 per 1M tokens, and routing.run has the lowest input price at $0.275 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Kimi K2.6 cost on Moonshot AI?

Moonshot AI charges $0.95 per 1M input tokens and $4 per 1M output tokens for Kimi K2.6.

### How many providers offer Kimi K2.6?

62 providers list Kimi K2.6 on Sovyron; 60 of them sell it at a metered per-token price.

### Is Kimi K2.6 free?

2 provider(s) list a free-tier offer: Kenari, Kenari. Free tiers usually have rate limits.

### Is Kimi K2.6 included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of Kimi K2.6?

Kimi K2.6 supports a 262k-token context window and up to 262k output tokens.

HTML page: https://sovyron.com/models/kimi-k2-6/
Full dataset: https://sovyron.com/data/catalog.json

---

# GLM-5.3 API prices

GLM-5.3 (glm) — 1.0M context, 1.0M max output.
65 metered per-token offers from 69 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| CrofAI | $0.4 | $1.4 | $0.06 | 1.0M |
| Merge Gateway | $0.7 | $2.2 | $0.13 | 1.0M |
| Vultr | $0.75 | $3 | — | 1.0M |
| DevPass (LLM Gateway) | $0.9 | $3 | $0.15 | 1.0M |
| LLM Gateway | $0.9 | $3 | $0.15 | 1.0M |
| Cortecs | $0.873 | $3.306 | $0.221 | 1.0M |
| engy | $0.98 | $3.08 | $0.18 | 328k |
| NanoGPT | $1 | $3.2 | $0.2 | 1.0M |
| AKI.IO | $1 | $3.5 | $0.25 | 524k |
| Deep Infra | $0.9 | $4 | $0.2 | 1.0M |
| Vancine | $1.12 | $3.52 | $0.208 | 1.0M |
| Melious | $1.1592 | $3.4776 | $0.2318 | 1.0M |
| ai& | $1 | $4 | $0.3 | 1.0M |
| IteraCompute | $1.2 | $3.5 | $0.26 | 1.0M |
| Alibaba (China) | $1.1 | $3.851 | $0.275 | 1.0M |
| AIHubMix | $1.1268 | $3.9438 | $0.2817 | 1.0M |
| Friendli | $1.26 | $3.96 | $0.234 | 1.0M |
| OrcaRouter | $1.26 | $3.96 | $0.234 | 1.0M |
| Requesty | $1.2 | $4.2 | $0.26 | 1.0M |
| Requesty (eu) | $1.2 | $4.2 | $0.26 | 1.0M |
| Vivgrid | $1.2 | $4.2 | $0.26 | 1.0M |
| CrossModel | $1.2 | $4.4 | $0.3 | 1.0M |
| 302.AI | $1.4 | $4.4 | — | 1.0M |
| Baseten | $1.4 | $4.4 | $0.14 | 1.0M |
| Cloudflare Workers AI | $1.4 | $4.4 | $0.26 | 1.0M |
| Eden AI | $1.4 | $4.4 | $0.26 | 1.0M |
| EmpirioLabs AI | $1.4 | $4.4 | $1.4 | 1.0M |
| Fireworks AI | $1.4 | $4.4 | $0.26 | 1.0M |
| Hugging Face | $1.4 | $4.4 | — | 1.0M |
| Inco | $1.4 | $4.4 | — | 1.0M |
| Kilo Gateway | $1.4 | $4.4 | $0.26 | 1.0M |
| LLM Gateway | $1.4 | $4.4 | $0.28 | 1.0M |
| LLM Gateway | $1.4 | $4.4 | $0.26 | 1.0M |
| LLM Gateway | $1.4 | $4.4 | $0.14 | 1.0M |
| LLM Gateway | $1.4 | $4.4 | $0.26 | 1.0M |
| LLM Gateway | $1.4 | $4.4 | $0.26 | 1.0M |
| LLM Gateway | $1.4 | $4.4 | $0.26 | 1.0M |
| LLM Gateway | $1.4 | $4.4 | $0.26 | 1.0M |
| Mistral | $1.4 | $4.4 | $0.14 | 1.0M |
| Nebius Token Factory | $1.4 | $4.4 | $1.4 | 1.0M |
| Ofox | $1.4 | $4.4 | $0.26 | 1.0M |
| Ollama Cloud | $1.4 | $4.4 | $0.26 | 1.0M |
| OpenCode Zen | $1.4 | $4.4 | $0.26 | 1.0M |
| OpenCode Go | $1.4 | $4.4 | $0.26 | 1.0M |
| OpenRouter | $1.4 | $4.4 | $0.14 | 1.0M |
| SiliconFlow | $1.4 | $4.4 | $0.26 | 1.0M |
| Synthetic | $1.4 | $4.4 | $0.26 | 524k |
| Tempr Gateway | $1.4 | $4.4 | $0.14 | 1.0M |
| Tempr Gateway | $1.4 | $4.4 | $0.26 | 1.0M |
| Together AI | $1.4 | $4.4 | $0.26 | 1.0M |
| TokenGo | $1.4 | $4.4 | $0.26 | 1.0M |
| Umans AI | $1.4 | $4.4 | $0.26 | 1.0M |
| Vercel AI Gateway | $1.4 | $4.4 | $0.14 | 1.0M |
| Z.AI | $1.4 | $4.4 | $0.26 | 1.0M |
| ZenMux | $1.4 | $4.4 | $0.26 | 1.0M |
| Zhipu AI | $1.4 | $4.4 | $0.26 | 1.0M |
| Neuralwatt | $1.45 | $4.5 | $0.145 | 1.0M |
| GreenPT | $1.2775 | $5.1102 | $0.3194 | 1.0M |
| Charm Hyper | $1.5243 | $4.7907 | $0.2831 | 1.0M |
| TensorX | $1.75 | $4.5 | $0.44 | 1.0M |
| Opper | $1.75 | $4.6488 | $0.44 | 1.0M |
| Bothub | $1.72 | $5.41 | — | 1.0M |
| Venice AI | $1.75 | $5.5 | $0.325 | 1.0M |
| Tinfoil | $1.8 | $5.75 | $0.45 | 1.0M |
| Privatemode AI | $1.791 | $6.6326 | $0.1733 | 1.0M |

## Summary

- Cheapest input: $0.4 per 1M tokens (CrofAI)
- Cheapest output: $1.4 per 1M tokens (CrofAI)
- First-party: $4.4 per 1M output tokens (Z.AI)
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China), Kenari, NaN, Nvidia, SCNet Token Plan, TokenRouter, Umans AI Coding Plan, Volcengine Ark Coding Plan, Z.AI Coding Plan, Zhipu AI Coding Plan
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China), ClinePass, SCNet Token Plan, Umans AI Coding Plan, Volcengine Ark Coding Plan, Z.AI Coding Plan, Zhipu AI Coding Plan
- Released: 2026-08-14
- Inputs: image, text

## FAQ

### What is the cheapest GLM-5.3 API?

As of Oct 4, 2026, CrofAI has the lowest GLM-5.3 output price at $1.4 per 1M tokens, and CrofAI has the lowest input price at $0.4 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GLM-5.3 cost on Z.AI?

Z.AI charges $1.4 per 1M input tokens and $4.4 per 1M output tokens for GLM-5.3.

### How many providers offer GLM-5.3?

69 providers list GLM-5.3 on Sovyron; 65 of them sell it at a metered per-token price.

### Is GLM-5.3 free?

4 provider(s) list a free-tier offer: Kenari, NaN, Nvidia, TokenRouter. Free tiers usually have rate limits.

### Is GLM-5.3 included in a subscription plan?

Yes. 7 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of GLM-5.3?

GLM-5.3 supports a 1.0M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/glm-5-3/
Full dataset: https://sovyron.com/data/catalog.json

---

# DeepSeek V4 Pro API prices

DeepSeek V4 Pro (deepseek-thinking) — 1.1M context, 1.0M max output.
63 metered per-token offers from 63 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| OpenRouter | $0.2088 | $0.4176 | $0.0174 | 1.0M |
| routing.run | $0.348 | $0.696 | — | 1.0M |
| CrofAI | $0.35 | $0.8 | $0.003 | 1.0M |
| CrofAI | $0.35 | $0.8 | $0.01 | 1.0M |
| EBCloud | $0.4286 | $0.8571 | — | 1.0M |
| Alibaba (China) | $0.435 | $0.87 | $0.0036 | 1.0M |
| Auriko | $0.435 | $0.87 | $0.0036 | 1.0M |
| Hugging Face | $0.435 | $0.87 | $0.0036 | 1.0M |
| DevPass (LLM Gateway) | $0.435 | $0.87 | $0.0036 | 1.1M |
| LLM Gateway | $0.435 | $0.87 | $0.0036 | 1.1M |
| LLM Gateway | $0.435 | $0.87 | $0.0036 | 1.0M |
| Modelis | $0.435 | $0.87 | — | 1.0M |
| Pioneer | $0.435 | $0.87 | $0.0036 | 1.0M |
| TokenGo | $0.435 | $0.87 | — | 1.0M |
| Vivgrid | $0.435 | $0.87 | $0.0036 | 1.0M |
| ZenMux | $0.435 | $0.87 | $0.0036 | 1.0M |
| OrcaRouter | $0.442 | $0.884 | $0.06 | 1.0M |
| AIHubMix | $0.478 | $0.956 | $0.0043 | 1.0M |
| DeepSeek | $0.66 | $1.98 | $0.022 | 1.0M |
| Eden AI | $0.66 | $1.98 | $0.022 | 1.0M |
| Ollama Cloud | $0.66 | $1.98 | $0.022 | 1.0M |
| Tempr Gateway | $0.66 | $1.98 | $0.022 | 1.0M |
| Vercel AI Gateway | $0.66 | $1.98 | $0.022 | 1.0M |
| above.dev | $0.726 | $2.178 | $0.0242 | 1.0M |
| UnoRouter | $0.8999 | $1.7999 | — | 1.0M |
| ai& | $1 | $2.5 | $0.25 | 1.0M |
| NanoGPT | $1.1 | $2.2 | $0.11 | 1.0M |
| NanoGPT | $1.1 | $2.2 | $0.11 | 1.0M |
| CoreWeave | $1.15 | $2.55 | $0.2 | 1.0M |
| Deep Infra | $1.3 | $2.6 | $0.1 | 1.0M |
| LLM Gateway | $1.3 | $2.6 | $0.1 | 1.0M |
| GMI Cloud | $1.392 | $2.784 | $0.116 | 1.0M |
| SiliconFlow | $1.5016 | $3.135 | $0.135 | 1.0M |
| LLM Gateway | $1.32 | $3.96 | $0.044 | 1.0M |
| LLM Gateway | $1.32 | $3.96 | $0.13 | 1.0M |
| Ofox | $1.32 | $3.96 | $0.044 | 1.0M |
| Requesty | $1.32 | $3.96 | $0.044 | 1.0M |
| Kilo Gateway | $1.6 | $3.2 | $0.135 | 1.0M |
| NovitaAI | $1.6 | $3.2 | $0.135 | 1.0M |
| CrossModel | $1.35 | $4.05 | $0.045 | 1.0M |
| Jalapeno Cloud | $1.6 | $3.38 | — | 1.0M |
| EmpirioLabs AI | $1.65 | $3.3 | $1.65 | 1.0M |
| Venice AI | $1.65 | $3.301 | $0.33 | 1.0M |
| AIHubMix | $1.69 | $3.38 | $0.13 | 1.0M |
| Cortecs | $1.7 | $3.4 | $0.15 | 1.0M |
| Abacus | $1.74 | $3.48 | $0.15 | 1.0M |
| Arcee | $1.74 | $3.48 | $0.2 | 512k |
| Azure | $1.74 | $3.48 | — | 1.0M |
| Baseten | $1.74 | $3.48 | $0.145 | 1.0M |
| Cloudflare AI Gateway | $1.74 | $3.48 | $0.145 | 131k |
| DigitalOcean | $1.74 | $3.48 | $0.348 | 1.0M |
| FastRouter | $1.74 | $3.48 | — | 1.0M |
| FrogBot | $1.74 | $3.48 | $0.14 | 128k |
| HPC-AI | $1.74 | $3.48 | $0.145 | 1.0M |
| Impossibl | $1.74 | $3.48 | $0.145 | 1.0M |
| Merge Gateway | $1.74 | $3.48 | $0.145 | 1.0M |
| Nebius Token Factory | $1.75 | $3.5 | $0.15 | 1.0M |
| Requesty (eu) | $1.75 | $3.5 | $0.44 | 1.0M |
| TensorX | $1.75 | $3.5 | $0.4375 | 1.0M |
| Opper | $1.7881 | $3.5762 | — | 1.0M |
| OpenCode Zen | $1.74 | $3.84 | $0.145 | 1.0M |
| Charm Hyper | $2.4 | $4.8 | $0.2 | 1.0M |
| LLM Gateway | $2.4 | $4.8 | $0.2 | 1.0M |

## Summary

- Cheapest input: $0.2088 per 1M tokens (OpenRouter)
- Cheapest output: $0.4176 per 1M tokens (OpenRouter)
- First-party: $1.98 per 1M output tokens (DeepSeek)
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China), Kenari, SCNet Token Plan, SenseNova (China), UnoRouter, Volcengine Ark Coding Plan
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China), ClinePass, SCNet Token Plan, Volcengine Ark Coding Plan
- Released: 2026-04-24
- Inputs: text

## FAQ

### What is the cheapest DeepSeek V4 Pro API?

As of Oct 4, 2026, OpenRouter has the lowest DeepSeek V4 Pro output price at $0.4176 per 1M tokens, and OpenRouter has the lowest input price at $0.2088 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does DeepSeek V4 Pro cost on DeepSeek?

DeepSeek charges $0.66 per 1M input tokens and $1.98 per 1M output tokens for DeepSeek V4 Pro.

### How many providers offer DeepSeek V4 Pro?

63 providers list DeepSeek V4 Pro on Sovyron; 63 of them sell it at a metered per-token price.

### Is DeepSeek V4 Pro free?

3 provider(s) list a free-tier offer: Kenari, SenseNova (China), UnoRouter. Free tiers usually have rate limits.

### Is DeepSeek V4 Pro included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of DeepSeek V4 Pro?

DeepSeek V4 Pro supports a 1.1M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/deepseek-v4-pro/
Full dataset: https://sovyron.com/data/catalog.json

---

# Kimi K2.7 Code API prices

Kimi K2.7 Code (kimi-k2) — 271k context, 262k max output.
54 metered per-token offers from 57 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| routing.run | $0.275 | $1.1 | — | 200k |
| CrofAI | $0.55 | $2.25 | $0.05 | 262k |
| Cortecs | $0.656 | $3.3 | $0.18 | 262k |
| Kilo Gateway | $0.6712 | $3.35 | $0.18 | 262k |
| OpenRouter | $0.6712 | $3.35 | $0.18 | 262k |
| Inceptron | $0.66 | $3.4 | $0.18 | 262k |
| Ambient | $0.69 | $3.49 | $0.14 | 262k |
| CoreWeave | $0.71 | $3.5 | $0.15 | 262k |
| ai& | $0.75 | $3.5 | $0.2 | 262k |
| Venice AI | $0.75 | $3.5 | $0.16 | 256k |
| Melious | $0.8114 | $3.4776 | $0.2202 | 262k |
| SiliconFlow | $0.8592 | $3.8 | $0.1799 | 262k |
| AIHubMix | $0.95 | $3.9995 | $0.1608 | 262k |
| 302.AI | $0.95 | $4 | — | 262k |
| Abacus | $0.95 | $4 | $0.19 | 262k |
| Azure | $0.95 | $4 | $0.19 | 262k |
| Baseten | $0.95 | $4 | $0.16 | 262k |
| Cloudflare Workers AI | $0.95 | $4 | $0.19 | 262k |
| Databricks | $0.95 | $4 | $0.19 | 262k |
| Eden AI | $0.95 | $4 | $0.19 | 262k |
| EmpirioLabs AI | $0.95 | $4 | $0.95 | 256k |
| HPC-AI | $0.95 | $4 | $0.19 | 256k |
| Hugging Face | $0.95 | $4 | — | 262k |
| Jalapeno Cloud | $0.95 | $4 | — | 271k |
| DevPass (LLM Gateway) | $0.95 | $4 | $0.19 | 262k |
| LLM Gateway | $0.95 | $4 | $0.19 | 262k |
| LLM Gateway | $0.95 | $4 | $0.19 | 262k |
| LLM Gateway | $0.95 | $4 | $0.19 | 262k |
| LLM Gateway | $0.95 | $4 | $0.19 | 262k |
| Merge Gateway | $0.95 | $4 | $0.19 | 262k |
| Moonshot AI | $0.95 | $4 | $0.19 | 262k |
| Moonshot AI (China) | $0.95 | $4 | $0.19 | 262k |
| NanoGPT | $0.95 | $4 | $0.19 | 262k |
| Nebius Token Factory | $0.95 | $4 | — | 262k |
| Neuralwatt | $0.95 | $4 | $0.095 | 262k |
| NovitaAI | $0.95 | $4 | $0.19 | 262k |
| Ofox | $0.95 | $4 | $0.19 | 262k |
| Ollama Cloud | $0.95 | $4 | $0.19 | 262k |
| OpenCode Zen | $0.95 | $4 | $0.19 | 262k |
| OpenCode Go | $0.95 | $4 | $0.19 | 262k |
| OrcaRouter | $0.95 | $4 | $0.19 | 262k |
| Perplexity Agent | $0.95 | $4 | $0.19 | 262k |
| Pioneer | $0.95 | $4 | $0.19 | 256k |
| Requesty | $0.95 | $4 | $0.19 | 262k |
| Synthetic | $0.95 | $4 | $0.95 | 262k |
| Tempr Gateway | $0.95 | $4 | $0.19 | 262k |
| Vercel AI Gateway | $0.95 | $4 | $0.19 | 256k |
| ZenMux | $0.95 | $4 | $0.16 | 262k |
| GreenPT | $0.9006 | $4.389 | $0.1881 | 262k |
| CrossModel | $1 | $4.16 | $0.18 | 262k |
| OpenReason | $1.0022 | $4.22 | — | 262k |
| Charm Hyper | $1.0344 | $4.3552 | $0.2069 | 256k |
| Requesty (eu) | $1.25 | $4.5 | $0.31 | 262k |
| TensorX | $1.25 | $4.5 | $0.3125 | 262k |

## Summary

- Cheapest input: $0.275 per 1M tokens (routing.run)
- Cheapest output: $1.1 per 1M tokens (routing.run)
- First-party: $4 per 1M output tokens (Moonshot AI)
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China), Kenari, Kenari, SCNet Token Plan, Volcengine Ark Coding Plan, ZenMux
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China), ClinePass, GitHub Copilot, SCNet Token Plan, Volcengine Ark Coding Plan
- Released: 2026-06-12
- Inputs: image, pdf, text, video

## FAQ

### What is the cheapest Kimi K2.7 Code API?

As of Oct 4, 2026, routing.run has the lowest Kimi K2.7 Code output price at $1.1 per 1M tokens, and routing.run has the lowest input price at $0.275 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Kimi K2.7 Code cost on Moonshot AI?

Moonshot AI charges $0.95 per 1M input tokens and $4 per 1M output tokens for Kimi K2.7 Code.

### How many providers offer Kimi K2.7 Code?

57 providers list Kimi K2.7 Code on Sovyron; 54 of them sell it at a metered per-token price.

### Is Kimi K2.7 Code free?

3 provider(s) list a free-tier offer: Kenari, Kenari, ZenMux. Free tiers usually have rate limits.

### Is Kimi K2.7 Code included in a subscription plan?

Yes. 6 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of Kimi K2.7 Code?

Kimi K2.7 Code supports a 271k-token context window and up to 262k output tokens.

HTML page: https://sovyron.com/models/kimi-k2-7-code/
Full dataset: https://sovyron.com/data/catalog.json

---

# DeepSeek V4 Flash API prices

DeepSeek V4 Flash (deepseek-flash) — 1.1M context, 1.0M max output.
58 metered per-token offers from 60 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Merge Gateway | $0.035 | $0.07 | $0.007 | 1.0M |
| NanoGPT | $0.05 | $0.16 | $0.013 | 1.0M |
| DevPass (LLM Gateway) | $0.065 | $0.116 | $0.012 | 1.1M |
| UnoRouter | $0.0625 | $0.125 | — | 1.0M |
| LLM Gateway | $0.08 | $0.18 | $0.016 | 1.0M |
| Deep Infra | $0.09 | $0.18 | $0.018 | 1.0M |
| TokenGo | $0.098 | $0.196 | $0.028 | 1.0M |
| Modelis | $0.0983 | $0.1966 | — | 1.0M |
| Pioneer | $0.1 | $0.2 | $0.0197 | 1.0M |
| GMI Cloud | $0.112 | $0.224 | $0.022 | 1.0M |
| routing.run | $0.112 | $0.224 | — | 1.0M |
| CrofAI | $0.12 | $0.21 | $0.003 | 1.0M |
| Vercel AI Gateway | $0.13 | $0.26 | $0.028 | 1.0M |
| SiliconFlow | $0.13 | $0.28 | $0.028 | 1.0M |
| ai& | $0.15 | $0.25 | $0.08 | 1.0M |
| Abacus | $0.14 | $0.28 | $0.03 | 1.0M |
| AIHubMix | $0.14 | $0.28 | $0.028 | 1.0M |
| Alibaba (China) | $0.14 | $0.28 | $0.0028 | 1.0M |
| Ambient | $0.14 | $0.28 | $0.028 | 1.0M |
| Arcee | $0.14 | $0.28 | $0.028 | 1.0M |
| Auriko | $0.14 | $0.28 | $0.0028 | 1.0M |
| DigitalOcean | $0.14 | $0.28 | $0.028 | 1.0M |
| EmpirioLabs AI | $0.14 | $0.28 | $0.14 | 1.0M |
| HPC-AI | $0.14 | $0.28 | $0.028 | 1.0M |
| Hugging Face | $0.14 | $0.28 | — | 1.0M |
| Jalapeno Cloud | $0.14 | $0.28 | — | 1.0M |
| Kilo Gateway | $0.14 | $0.28 | $0.028 | 1.0M |
| LLM Gateway | $0.14 | $0.28 | $0.028 | 1.1M |
| LLM Gateway | $0.14 | $0.28 | $0.0028 | 1.0M |
| LLM Gateway | $0.14 | $0.28 | $0.03 | 164k |
| NanoGPT | $0.14 | $0.28 | $0.0028 | 1.0M |
| NanoGPT | $0.14 | $0.28 | $0.0028 | 1.0M |
| Neuralwatt | $0.14 | $0.28 | $0.028 | 1.0M |
| NovitaAI | $0.14 | $0.28 | $0.028 | 1.0M |
| OpenCode Zen | $0.14 | $0.28 | $0.028 | 1.0M |
| SiliconFlow (China) | $0.14 | $0.28 | $0.003 | 1.0M |
| Umans AI | $0.14 | $0.28 | $0.028 | 1.0M |
| CoreWeave | $0.14 | $0.28 | $0.07 | 1.0M |
| ZenMux | $0.14 | $0.28 | $0.0028 | 1.0M |
| EBCloud | $0.143 | $0.2857 | — | 1.0M |
| OrcaRouter | $0.147 | $0.295 | $0.02 | 1.0M |
| Vivgrid | $0.15 | $0.3 | $0.03 | 1.0M |
| AIHubMix | $0.154 | $0.308 | $0.0308 | 1.0M |
| Charm Hyper | $0.2 | $0.4 | $0.04 | 1.0M |
| LLM Gateway | $0.2 | $0.4 | $0.04 | 1.0M |
| Eden AI | $0.15 | $0.6 | $0.003 | 1.0M |
| OpenCode Go | $0.15 | $0.6 | $0.003 | 1.0M |
| Azure | $0.19 | $0.51 | — | 1.0M |
| Impossibl | $0.19 | $0.51 | $0.028 | 1.0M |
| LLM Gateway | $0.22 | $0.66 | $0.007 | 1.0M |
| Ollama Cloud | $0.22 | $0.66 | $0.007 | 1.0M |
| Kilo Gateway | $0.0152 | $1.28 | $0.0152 | 1.0M |
| OpenRouter | $0.0152 | $1.28 | $0.0152 | 1.0M |
| OpenRouter | $0.0224 | $1.28 | $0.0224 | 1.0M |
| Requesty | $0.28 | $0.56 | $0.07 | 1.0M |
| Opper | $0.25 | $0.66 | — | 1.0M |
| CrossModel | $0.3 | $1.2 | $0.006 | 1.0M |
| Ofox | $0.44 | $1.32 | $0.014 | 1.0M |

## Summary

- Cheapest input: $0.0152 per 1M tokens (Kilo Gateway)
- Cheapest output: $0.07 per 1M tokens (Merge Gateway)
- First-party: not listed separately
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China), InferX, Kenari, Kenari, OrcaRouter, Pendra, SCNet Token Plan, SenseNova (China), Umans AI Coding Plan, UnoRouter, Volcengine Ark Coding Plan
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China), ClinePass, SCNet Token Plan, Umans AI Coding Plan, Volcengine Ark Coding Plan
- Released: 2026-04-24
- Inputs: image, text

## FAQ

### What is the cheapest DeepSeek V4 Flash API?

As of Oct 4, 2026, Merge Gateway has the lowest DeepSeek V4 Flash output price at $0.07 per 1M tokens, and Kilo Gateway has the lowest input price at $0.0152 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer DeepSeek V4 Flash?

60 providers list DeepSeek V4 Flash on Sovyron; 58 of them sell it at a metered per-token price.

### Is DeepSeek V4 Flash free?

7 provider(s) list a free-tier offer: InferX, Kenari, Kenari, OrcaRouter, Pendra, SenseNova (China), UnoRouter. Free tiers usually have rate limits.

### Is DeepSeek V4 Flash included in a subscription plan?

Yes. 4 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of DeepSeek V4 Flash?

DeepSeek V4 Flash supports a 1.1M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/deepseek-v4-flash/
Full dataset: https://sovyron.com/data/catalog.json

---

# DeepSeek V4.1 Flash API prices

DeepSeek V4.1 Flash (deepseek-flash) — 1.1M context, 1.0M max output.
58 metered per-token offers from 55 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| engy | $0.04 | $0.08 | $0.008 | 328k |
| AMD | $0.14 | $0.28 | $0.0028 | 1.0M |
| NanoGPT | $0.13 | $0.52 | $0.006 | 1.0M |
| DevPass (LLM Gateway) | $0.15 | $0.55 | $0.005 | 1.1M |
| 302.AI | $0.15 | $0.6 | $0.003 | 1.0M |
| DeepSeek | $0.15 | $0.6 | $0.003 | 1.0M |
| Eden AI | $0.15 | $0.6 | $0.015 | 1.0M |
| LLM Gateway | $0.15 | $0.6 | $0.003 | 1.1M |
| LLM Gateway | $0.15 | $0.6 | $0.01 | 1.0M |
| Merge Gateway | $0.15 | $0.6 | $0.003 | 1.0M |
| Neuralwatt | $0.15 | $0.6 | $0.015 | 1.0M |
| Ollama Cloud | $0.15 | $0.6 | $0.003 | 1.0M |
| OpenCode Go | $0.15 | $0.6 | $0.003 | 1.0M |
| Tempr Gateway | $0.15 | $0.6 | $0.003 | 1.0M |
| Umans AI | $0.15 | $0.6 | $0.028 | 1.0M |
| Vultr | $0.15 | $0.6 | — | 1.0M |
| ZenMux | $0.15 | $0.6 | $0.003 | 1.0M |
| AIHubMix | $0.155 | $0.62 | $0.0031 | 1.0M |
| above.dev | $0.165 | $0.66 | $0.0033 | 1.0M |
| Deep Infra | $0.2 | $0.6 | $0.006 | 1.0M |
| Eden AI | $0.2 | $0.6 | $0.006 | 1.0M |
| LLM Gateway | $0.2 | $0.6 | $0.006 | 1.0M |
| Cortecs | $0.201 | $0.6 | $0.004 | 1.0M |
| CoreWeave | $0.2 | $0.65 | $0.03 | 1.0M |
| LLM Gateway | $0.22 | $0.66 | $0.007 | 1.0M |
| Ofox | $0.21 | $0.84 | $0.0042 | 1.0M |
| ai& | $0.3 | $0.6 | $0.02 | 1.0M |
| Vancine | $0.24 | $0.96 | $0.0048 | 1.0M |
| Melious | $0.2318 | $1.1592 | $0.0116 | 1.0M |
| GreenPT | $0.2556 | $1.2778 | $0.0128 | 1.0M |
| Alibaba (China) | $0.2975 | $1.1902 | $0.0149 | 1.0M |
| Baseten | $0.3 | $1.2 | $0.03 | 1.0M |
| CrossModel | $0.3 | $1.2 | $0.006 | 1.0M |
| DigitalOcean | $0.3 | $1.2 | $0.006 | 1.0M |
| Eden AI | $0.3 | $1.2 | $0.3 | 1.0M |
| Eden AI | $0.3 | $1.2 | $0.006 | 1.0M |
| EmpirioLabs AI | $0.3 | $1.2 | $0.3 | 1.0M |
| Fireworks AI | $0.3 | $1.2 | $0.006 | 1.0M |
| Hugging Face | $0.3 | $1.2 | — | 1.0M |
| Kilo Gateway | $0.3 | $1.2 | $0.006 | 1.0M |
| LLM Gateway | $0.3 | $1.2 | $0.03 | 1.0M |
| LLM Gateway | $0.3 | $1.2 | $0.006 | 1.0M |
| LLM Gateway | $0.3 | $1.2 | $0.006 | 1.0M |
| Nebius Token Factory | $0.3 | $1.2 | $0.3 | 1.0M |
| OpenCode Zen | $0.3 | $1.2 | $0.006 | 1.0M |
| Together AI | $0.3 | $1.2 | $0.006 | 1.0M |
| Venice AI | $0.3 | $1.2 | $0.0075 | 1.0M |
| Vercel AI Gateway | $0.3 | $1.2 | $0.007 | 1.0M |
| Vivgrid | $0.31 | $1.23 | $0.01 | 1.0M |
| Charm Hyper | $0.33 | $1.31 | $0.03 | 1.0M |
| OpenRouter | $0.003 | $2.4 | $0.003 | 1.0M |
| Eden AI | $0.5 | $1.5 | $0.125 | 1.0M |
| Requesty | $0.5 | $1.5 | $0.05 | 1.0M |
| Requesty (eu) | $0.5 | $1.5 | $0.05 | 1.0M |
| Synthetic | $0.6 | $1.2 | $0.03 | 524k |
| TensorX | $0.5 | $1.5 | $0.13 | 1.0M |
| Tinfoil | $0.65 | $1.45 | $0.13 | 1.0M |
| Inco | $0.6 | $2.4 | — | 1.0M |

## Summary

- Cheapest input: $0.003 per 1M tokens (OpenRouter)
- Cheapest output: $0.08 per 1M tokens (engy)
- First-party: $0.6 per 1M output tokens (DeepSeek)
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China), Kenari, NaN, Nvidia, SCNet Token Plan, Umans AI Coding Plan
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China), ClinePass, SCNet Token Plan, Umans AI Coding Plan
- Released: 2026-09-10
- Inputs: image, text

## FAQ

### What is the cheapest DeepSeek V4.1 Flash API?

As of Oct 4, 2026, engy has the lowest DeepSeek V4.1 Flash output price at $0.08 per 1M tokens, and OpenRouter has the lowest input price at $0.003 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does DeepSeek V4.1 Flash cost on DeepSeek?

DeepSeek charges $0.15 per 1M input tokens and $0.6 per 1M output tokens for DeepSeek V4.1 Flash.

### How many providers offer DeepSeek V4.1 Flash?

55 providers list DeepSeek V4.1 Flash on Sovyron; 58 of them sell it at a metered per-token price.

### Is DeepSeek V4.1 Flash free?

3 provider(s) list a free-tier offer: Kenari, NaN, Nvidia. Free tiers usually have rate limits.

### Is DeepSeek V4.1 Flash included in a subscription plan?

Yes. 4 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash supports a 1.1M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/deepseek-v4-1-flash/
Full dataset: https://sovyron.com/data/catalog.json

---

# GLM-5.1 API prices

GLM-5.1 (glm) — 205k context, 203k max output.
51 metered per-token offers from 51 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| CrofAI | $0.45 | $2.15 | $0.08 | 203k |
| HPC-AI | $0.615 | $2.46 | $0.133 | 202k |
| NanoGPT | $0.75 | $2.6 | $0.15 | 200k |
| DevPass (LLM Gateway) | $0.931 | $2.93 | $0.173 | 205k |
| Alibaba (China) | $0.825 | $3.301 | $0.17 | 203k |
| EmpirioLabs AI | $0.825 | $3.301 | $0.165 | 202k |
| AIHubMix | $0.84 | $3.38 | $0.169 | 200k |
| AIHubMix | $0.845 | $3.38 | $0.1831 | 200k |
| EBCloud | $0.8571 | $3.4286 | — | 200k |
| GMI Cloud | $0.98 | $3.08 | $0.182 | 203k |
| Pioneer | $0.98 | $3.08 | $0.182 | 202k |
| ZenMux | $0.8781 | $3.5126 | $0.1903 | 200k |
| Hugging Face | $1 | $3.2 | $0.2 | 203k |
| Ollama Cloud | $1 | $3.2 | $0.2 | 203k |
| Wafer | $1 | $3.2 | $0.1 | 203k |
| FastRouter | $1.05 | $3.5 | — | 200k |
| CrossModel | $1 | $3.8 | $0.2 | 200k |
| DInference | $1.25 | $3.89 | — | 200k |
| Crusoe | $1.2 | $4.4 | $0.25 | 200k |
| Baseten | $1.3 | $4.3 | $0.26 | 203k |
| DigitalOcean | $1.3 | $4.3 | $0.26 | 164k |
| Cortecs | $1.384 | $4.348 | $0.346 | 203k |
| Jalapeno Cloud | $1.38 | $4.4 | — | 203k |
| LLM Gateway | $1.38 | $4.4 | $0.26 | 205k |
| NovitaAI | $1.38 | $4.4 | $0.26 | 205k |
| 302.AI | $1.4 | $4.4 | — | 200k |
| Abacus | $1.4 | $4.4 | $0.26 | 205k |
| Ambient | $1.4 | $4.4 | free | 203k |
| Auriko | $1.4 | $4.4 | $0.26 | 200k |
| Eden AI | $1.4 | $4.4 | $0.26 | 203k |
| Friendli | $1.4 | $4.4 | $0.26 | 203k |
| FrogBot | $1.4 | $4.4 | $0.26 | 198k |
| Impossibl | $1.4 | $4.4 | $0.26 | 200k |
| Kilo Gateway | $1.4 | $4.4 | $0.26 | 203k |
| LLM Gateway | $1.4 | $4.4 | $0.26 | 200k |
| LLM Gateway | $1.4 | $4.4 | $0.26 | 200k |
| Merge Gateway | $1.4 | $4.4 | $0.26 | 200k |
| Ofox | $1.4 | $4.4 | $0.26 | 200k |
| OpenCode Zen | $1.4 | $4.4 | $0.26 | 205k |
| OpenRouter | $1.4 | $4.4 | $0.26 | 205k |
| OrcaRouter | $1.4 | $4.4 | $0.26 | 200k |
| Requesty | $1.4 | $4.4 | $0.26 | 200k |
| Requesty (eu) | $1.4 | $4.4 | $1.4 | 200k |
| Tempr Gateway | $1.4 | $4.4 | $0.26 | 200k |
| TensorX | $1.4 | $4.4 | $0.35 | 203k |
| TokenGo | $1.4 | $4.4 | $0.26 | 200k |
| Vercel AI Gateway | $1.4 | $4.4 | $0.26 | 203k |
| Z.AI | $1.4 | $4.4 | $0.26 | 200k |
| Zhipu AI | $1.4 | $4.4 | $0.26 | 200k |
| Melious | $1.507 | $4.6368 | $0.3709 | 203k |
| Venice AI | $1.54 | $4.84 | $0.286 | 200k |

## Summary

- Cheapest input: $0.45 per 1M tokens (CrofAI)
- Cheapest output: $2.15 per 1M tokens (CrofAI)
- First-party: $4.4 per 1M output tokens (Z.AI)
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China), Kenari, SCNet Token Plan
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China), SCNet Token Plan
- Released: 2026-04-07
- Inputs: text

## FAQ

### What is the cheapest GLM-5.1 API?

As of Oct 4, 2026, CrofAI has the lowest GLM-5.1 output price at $2.15 per 1M tokens, and CrofAI has the lowest input price at $0.45 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GLM-5.1 cost on Z.AI?

Z.AI charges $1.4 per 1M input tokens and $4.4 per 1M output tokens for GLM-5.1.

### How many providers offer GLM-5.1?

51 providers list GLM-5.1 on Sovyron; 51 of them sell it at a metered per-token price.

### Is GLM-5.1 free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is GLM-5.1 included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of GLM-5.1?

GLM-5.1 supports a 205k-token context window and up to 203k output tokens.

HTML page: https://sovyron.com/models/glm-5-1/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Sonnet 4.6 API prices

Claude Sonnet 4.6 (claude-sonnet) — 1.0M context, 128k max output.
53 metered per-token offers from 50 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Xpersona | $0.9 | $5.55 | $0.09 | 200k |
| Poe | $2.6 | $13 | $0.26 | 983k |
| 302.AI | $3 | $15 | — | 1.0M |
| Abacus | $3 | $15 | — | 1.0M |
| AIHubMix | $3 | $15 | $0.3 | 1.0M |
| Amazon Bedrock (global) | $3 | $15 | $0.3 | 1.0M |
| Anthropic | $3 | $15 | $0.3 | 1.0M |
| Auriko | $3 | $15 | $0.3 | 1.0M |
| Azure | $3 | $15 | $0.3 | 1.0M |
| Azure Cognitive Services | $3 | $15 | $0.3 | 1.0M |
| Cloudflare AI Gateway | $3 | $15 | $0.3 | 1.0M |
| CrossModel | $3 | $15 | $0.3 | 1.0M |
| DaoXE | $3 | $15 | $0.3 | 1.0M |
| Databricks | $3 | $15 | $0.3 | 1.0M |
| DigitalOcean | $3 | $15 | $0.3 | 200k |
| Eden AI | $3 | $15 | $0.3 | 1.0M |
| FastRouter | $3 | $15 | — | 1.0M |
| FreeModel | $3 | $15 | $0.3 | 1.0M |
| FrogBot | $3 | $15 | $0.3 | 200k |
| GMI Cloud | $3 | $15 | $0.3 | 410k |
| Vertex | $3 | $15 | $0.3 | 1.0M |
| Vertex (Anthropic) | $3 | $15 | $0.3 | 1.0M |
| Impossibl | $3 | $15 | $0.3 | 1.0M |
| Kilo Gateway | $3 | $15 | $0.3 | 1.0M |
| DevPass (LLM Gateway) | $3 | $15 | $0.3 | 1.0M |
| LLM Gateway | $3 | $15 | $0.3 | 1.0M |
| LLM Gateway | $3 | $15 | $0.3 | 1.0M |
| LLM Gateway | $3 | $15 | $0.3 | 1.0M |
| Merge Gateway | $3 | $15 | $0.3 | 1.0M |
| Modelis | $3 | $15 | — | 1.0M |
| NanoGPT | $3 | $15 | $0.3 | 1.0M |
| NEAR AI Cloud | $3 | $15 | $0.3 | 1.0M |
| Neon | $3 | $15 | $0.3 | 1.0M |
| Ofox | $3 | $15 | $0.3 | 1.0M |
| OpenCode Zen | $3 | $15 | $0.3 | 1.0M |
| OpenRouter | $3 | $15 | $0.3 | 1.0M |
| OrcaRouter | $3 | $15 | $0.3 | 1.0M |
| Perplexity Agent | $3 | $15 | $0.3 | 200k |
| Pioneer | $3 | $15 | $0.3 | 1.0M |
| Requesty | $3 | $15 | $0.3 | 1.0M |
| routing.run | $3 | $15 | — | 1.0M |
| SAP AI Core | $3 | $15 | $0.3 | 1.0M |
| Tempr Gateway | $3 | $15 | $0.3 | 1.0M |
| Vercel AI Gateway | $3 | $15 | $0.3 | 1.0M |
| ZenMux | $3 | $15 | $0.3 | 1.0M |
| Cortecs | $3.196 | $15.94 | $0.32 | 1.0M |
| Amazon Bedrock | $3.3 | $16.5 | $0.33 | 1.0M |
| Amazon Bedrock (eu) | $3.3 | $16.5 | $0.33 | 1.0M |
| Amazon Bedrock (jp) | $3.3 | $16.5 | $0.33 | 1.0M |
| Amazon Bedrock (us) | $3.3 | $16.5 | $0.33 | 1.0M |
| Opper | $3.3 | $16.5 | $0.33 | 1.0M |
| Requesty (eu) | $3.3 | $16.5 | $0.3 | 1.0M |
| Venice AI | $3.6 | $18 | $0.36 | 1.0M |

## Summary

- Cheapest input: $0.9 per 1M tokens (Xpersona)
- Cheapest output: $5.55 per 1M tokens (Xpersona)
- First-party: $15 per 1M output tokens (Anthropic)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-02-17
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Sonnet 4.6 API?

As of Oct 4, 2026, Xpersona has the lowest Claude Sonnet 4.6 output price at $5.55 per 1M tokens, and Xpersona has the lowest input price at $0.9 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Claude Sonnet 4.6 cost on Anthropic?

Anthropic charges $3 per 1M input tokens and $15 per 1M output tokens for Claude Sonnet 4.6.

### How many providers offer Claude Sonnet 4.6?

50 providers list Claude Sonnet 4.6 on Sovyron; 53 of them sell it at a metered per-token price.

### Is Claude Sonnet 4.6 free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is Claude Sonnet 4.6 included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Claude Sonnet 4.6?

Claude Sonnet 4.6 supports a 1.0M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/claude-sonnet-4-6/
Full dataset: https://sovyron.com/data/catalog.json

---

# MiniMax-M3 API prices

MiniMax-M3 (minimax) — 1.0M context, 1.0M max output.
48 metered per-token offers from 51 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Vultr | $0.2 | $0.9 | — | 524k |
| EmpirioLabs AI | $0.225 | $0.9 | $0.045 | 1.0M |
| CoreWeave | $0.23 | $0.96 | $0.05 | 262k |
| Vancine | $0.24 | $0.96 | $0.048 | 1.0M |
| Deep Infra | $0.28 | $1.1 | $0.056 | 524k |
| Lilac | $0.28 | $1.1 | $0.05 | 1.0M |
| AIHubMix | $0.288 | $1.152 | — | 1.0M |
| IteraCompute | $0.29 | $1.2 | $0.08 | 1.0M |
| Abacus | $0.3 | $1.2 | — | 1.0M |
| Cortecs | $0.3 | $1.2 | $0.06 | 1.0M |
| Eden AI | $0.3 | $1.2 | $0.06 | 524k |
| Fireworks AI | $0.3 | $1.2 | $0.06 | 512k |
| Hugging Face | $0.3 | $1.2 | — | 524k |
| Inco | $0.3 | $1.2 | — | 1.0M |
| Jalapeno Cloud | $0.3 | $1.2 | — | 524k |
| Kilo Gateway | $0.3 | $1.2 | $0.06 | 524k |
| DevPass (LLM Gateway) | $0.3 | $1.2 | $0.06 | 1.0M |
| LLM Gateway | $0.3 | $1.2 | $0.06 | 1.0M |
| LLM Gateway | $0.3 | $1.2 | $0.06 | 524k |
| Merge Gateway | $0.3 | $1.2 | $0.06 | 1.0M |
| MiniMax (minimax.io) | $0.3 | $1.2 | $0.06 | 1.0M |
| MiniMax (minimax.cn) | $0.3 | $1.2 | $0.06 | 1.0M |
| NanoGPT | $0.3 | $1.2 | $0.06 | 512k |
| Nebius Token Factory | $0.3 | $1.2 | — | 1.0M |
| OpenCode Zen | $0.3 | $1.2 | $0.06 | 512k |
| OpenCode Go | $0.3 | $1.2 | $0.06 | 1.0M |
| OpenRouter | $0.3 | $1.2 | $0.06 | 1.0M |
| OrcaRouter | $0.3 | $1.2 | $0.06 | 1.0M |
| Pioneer | $0.3 | $1.2 | $0.06 | 1.0M |
| Requesty | $0.3 | $1.2 | $0.06 | 1.0M |
| SiliconFlow | $0.3 | $1.2 | $0.06 | 1.0M |
| Tempr Gateway | $0.3 | $1.2 | $0.06 | 1.0M |
| Together AI | $0.3 | $1.2 | $0.06 | 524k |
| Venice AI | $0.3 | $1.2 | $0.06 | 524k |
| Vercel AI Gateway | $0.3 | $1.2 | $0.06 | 512k |
| Charm Hyper | $0.3266 | $1.3066 | $0.0642 | 512k |
| CrossModel | $0.33 | $1.32 | $0.066 | 1.0M |
| Wafer | $0.33 | $1.32 | $0.07 | 1.0M |
| Synthetic | $0.6 | $1.2 | $0.6 | 524k |
| Requesty (eu) | $0.4 | $2 | $0.1 | 1.0M |
| TensorX | $0.4 | $2 | $0.1 | 1.0M |
| GMI Cloud | $0.6 | $2.4 | $0.12 | 1.0M |
| LLM Gateway | $0.6 | $2.4 | $0.12 | 512k |
| Ofox | $0.6 | $2.4 | $0.12 | 1.0M |
| Ollama Cloud | $0.6 | $2.4 | $0.12 | 512k |
| Opper | $0.6 | $2.4 | $0.12 | 1.0M |
| ZenMux | $0.6 | $2.4 | — | 1.0M |
| 302.AI | $0.72 | $2.88 | — | 1.0M |

## Summary

- Cheapest input: $0.2 per 1M tokens (Vultr)
- Cheapest output: $0.9 per 1M tokens (Vultr)
- First-party: $1.2 per 1M output tokens (MiniMax (minimax.io))
- Free offers: Kenari, MiniMax Token Plan (minimax.cn), MiniMax Token Plan (minimax.io), SCNet Token Plan, Volcengine Ark Coding Plan
- Subscription plans (not per-token): ClinePass, MiniMax Token Plan (minimax.cn), MiniMax Token Plan (minimax.io), SCNet Token Plan, Volcengine Ark Coding Plan
- Released: 2026-06-01
- Inputs: image, pdf, text, video

## FAQ

### What is the cheapest MiniMax-M3 API?

As of Oct 4, 2026, Vultr has the lowest MiniMax-M3 output price at $0.9 per 1M tokens, and Vultr has the lowest input price at $0.2 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does MiniMax-M3 cost on MiniMax (minimax.io)?

MiniMax (minimax.io) charges $0.3 per 1M input tokens and $1.2 per 1M output tokens for MiniMax-M3.

### How many providers offer MiniMax-M3?

51 providers list MiniMax-M3 on Sovyron; 48 of them sell it at a metered per-token price.

### Is MiniMax-M3 free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is MiniMax-M3 included in a subscription plan?

Yes. 4 flat-rate plan(s) include it; the cheapest is OpenCode OpenCode Go at $10/month.

### What is the context window of MiniMax-M3?

MiniMax-M3 supports a 1.0M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/minimax-m3/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.5 API prices

GPT-5.5 (gpt) — 1.1M context, 131k max output.
46 metered per-token offers from 47 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| UnoRouter | $0.1875 | $1.125 | — | 1.1M |
| Xpersona | $1.5 | $12 | $0.15 | 1.1M |
| FrogBot | $2.5 | $15 | $0.25 | 272k |
| Xpersona | $3 | $18 | $0.3 | 1.0M |
| Ofox | $4 | $24 | $0.4 | 1.1M |
| Poe | $4.5455 | $27.2727 | $0.4545 | 400k |
| 302.AI | $5 | $30 | — | 1.1M |
| Abacus | $5 | $30 | $0.5 | 1.0M |
| AI-ROUTER | $5 | $30 | $0.5 | 1.1M |
| AIHubMix | $5 | $30 | $0.5 | 1.1M |
| Azure | $5 | $30 | $0.5 | 1.1M |
| Azure Cognitive Services | $5 | $30 | $0.5 | 1.1M |
| Cloudflare AI Gateway | $5 | $30 | — | 1.0M |
| CrossModel | $5 | $30 | $0.5 | 1.1M |
| DaoXE | $5 | $30 | $0.5 | 1.1M |
| Databricks | $5 | $30 | $0.5 | 1.1M |
| DigitalOcean | $5 | $30 | $0.5 | 1.0M |
| Eden AI | $5 | $30 | $0.5 | 1.1M |
| FastRouter | $5 | $30 | — | 1.1M |
| FreeModel | $5 | $30 | $0.5 | 1.1M |
| GMI Cloud | $5 | $30 | $0.5 | 1.1M |
| HPC-AI | $5 | $30 | $0.5 | 1.1M |
| Impossibl | $5 | $30 | $0.5 | 1.1M |
| Kilo Gateway | $5 | $30 | $0.5 | 1.1M |
| DevPass (LLM Gateway) | $5 | $30 | $0.5 | 1.1M |
| LLM Gateway | $5 | $30 | $0.5 | 1.1M |
| LLM Gateway | $5 | $30 | $0.5 | 1.1M |
| Merge Gateway | $5 | $30 | $0.5 | 1.1M |
| NanoGPT | $5 | $30 | $0.5 | 1.1M |
| NEAR AI Cloud | $5 | $30 | $0.5 | 1.1M |
| Neon | $5 | $30 | $0.5 | 1.1M |
| OpenAI | $5 | $30 | $0.5 | 1.1M |
| OpenCode Zen | $5 | $30 | $0.5 | 1.1M |
| OpenRouter | $5 | $30 | $0.5 | 1.1M |
| Opper | $5 | $30 | $0.5 | 1.1M |
| OrcaRouter | $5 | $30 | $0.5 | 1.1M |
| Perplexity Agent | $5 | $30 | $0.5 | 1.1M |
| Pioneer | $5 | $30 | $0.5 | 1.1M |
| SAP AI Core | $5 | $30 | $0.5 | 1.1M |
| Vercel AI Gateway | $5 | $30 | $0.5 | 1.0M |
| Vivgrid | $5 | $30 | $0.5 | 1.1M |
| ZenMux | $5 | $30 | $0.5 | 1.1M |
| Amazon Bedrock | $5.5 | $33 | $0.55 | 1.0M |
| Requesty | $5.5 | $33 | $0.55 | 1.1M |
| Requesty (eu) | $5.5 | $33 | $0.55 | 1.1M |
| Venice AI | $6.25 | $37.5 | $0.625 | 1.0M |

## Summary

- Cheapest input: $0.1875 per 1M tokens (UnoRouter)
- Cheapest output: $1.125 per 1M tokens (UnoRouter)
- First-party: $30 per 1M output tokens (OpenAI)
- Free offers: Kenari, UnoRouter
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-04-23
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.5 API?

As of Oct 4, 2026, UnoRouter has the lowest GPT-5.5 output price at $1.125 per 1M tokens, and UnoRouter has the lowest input price at $0.1875 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5.5 cost on OpenAI?

OpenAI charges $5 per 1M input tokens and $30 per 1M output tokens for GPT-5.5.

### How many providers offer GPT-5.5?

47 providers list GPT-5.5 on Sovyron; 46 of them sell it at a metered per-token price.

### Is GPT-5.5 free?

2 provider(s) list a free-tier offer: Kenari, UnoRouter. Free tiers usually have rate limits.

### Is GPT-5.5 included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of GPT-5.5?

GPT-5.5 supports a 1.1M-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/gpt-5-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Haiku 4.5 API prices

Claude Haiku 4.5 (claude-haiku) — 200k context, 128k max output.
57 metered per-token offers from 47 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| QiHang | $0.14 | $0.71 | — | 200k |
| Xpersona | $0.6 | $3.7 | $0.06 | 200k |
| Poe | $0.85 | $4.3 | $0.085 | 192k |
| Cortecs | $0.996 | $4.982 | $0.099 | 200k |
| 302.AI | $1 | $5 | — | 200k |
| Abacus | $1 | $5 | — | 200k |
| Amazon Bedrock | $1 | $5 | $0.1 | 200k |
| Amazon Bedrock (global) | $1 | $5 | $0.1 | 200k |
| Anthropic | $1 | $5 | $0.1 | 200k |
| Anthropic | $1 | $5 | $0.1 | 200k |
| Azure | $1 | $5 | $0.1 | 200k |
| Azure Cognitive Services | $1 | $5 | $0.1 | 200k |
| Cloudflare AI Gateway | $1 | $5 | $0.1 | 200k |
| CrossModel | $1 | $5 | $0.1 | 200k |
| DaoXE | $1 | $5 | $0.1 | 200k |
| Databricks | $1 | $5 | $0.1 | 200k |
| DigitalOcean | $1 | $5 | $0.1 | 200k |
| FreeModel | $1 | $5 | $0.1 | 200k |
| FrogBot | $1 | $5 | $0.1 | 200k |
| Vertex | $1 | $5 | $0.1 | 200k |
| Vertex (Anthropic) | $1 | $5 | $0.1 | 200k |
| Helicone | $1 | $5 | $0.1 | 200k |
| Helicone | $1 | $5 | $0.1 | 200k |
| Impossibl | $1 | $5 | $0.1 | 200k |
| Kilo Gateway | $1 | $5 | $0.1 | 200k |
| DevPass (LLM Gateway) | $1 | $5 | $0.1 | 200k |
| DevPass (LLM Gateway) | $1 | $5 | $0.1 | 200k |
| LLM Gateway | $1 | $5 | $0.1 | 200k |
| LLM Gateway | $1 | $5 | $0.1 | 200k |
| LLM Gateway | $1 | $5 | $0.1 | 200k |
| LLM Gateway | $1 | $5 | $0.1 | 200k |
| LLM Gateway | $1 | $5 | $0.1 | 200k |
| Merge Gateway | $1 | $5 | $0.1 | 200k |
| NanoGPT | $1 | $5 | $0.1 | 200k |
| NEAR AI Cloud | $1 | $5 | $0.1 | 200k |
| Neon | $1 | $5 | $0.1 | 200k |
| Ofox | $1 | $5 | $0.1 | 200k |
| OpenCode Zen | $1 | $5 | $0.1 | 200k |
| OpenRouter | $1 | $5 | $0.1 | 200k |
| OrcaRouter | $1 | $5 | $0.1 | 200k |
| Perplexity Agent | $1 | $5 | $0.1 | 200k |
| Pioneer | $1 | $5 | $0.1 | 200k |
| Requesty | $1 | $5 | $0.1 | 200k |
| SAP AI Core | $1 | $5 | $0.1 | 200k |
| Tempr Gateway | $1 | $5 | $0.1 | 200k |
| Tempr Gateway | $1 | $5 | $0.1 | 200k |
| Vercel AI Gateway | $1 | $5 | $0.1 | 200k |
| ZenMux | $1 | $5 | $0.1 | 200k |
| AIHubMix | $1.1 | $5.5 | $0.11 | 200k |
| Amazon Bedrock (au) | $1.1 | $5.5 | $0.11 | 200k |
| Amazon Bedrock (eu) | $1.1 | $5.5 | $0.11 | 200k |
| Amazon Bedrock (india) | $1.1 | $5.5 | $0.11 | 200k |
| Amazon Bedrock (jp) | $1.1 | $5.5 | $0.11 | 200k |
| Amazon Bedrock (us) | $1.1 | $5.5 | $0.11 | 200k |
| Opper | $1.1 | $5.5 | $0.11 | 200k |
| Requesty | $1.1 | $5.5 | $0.11 | 200k |
| UnoRouter | $1.2 | $6 | — | 200k |

## Summary

- Cheapest input: $0.14 per 1M tokens (QiHang)
- Cheapest output: $0.71 per 1M tokens (QiHang)
- First-party: $5 per 1M output tokens (Anthropic)
- Free offers: none
- Subscription plans (not per-token): GitHub Copilot
- Released: 2025-10-15
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Haiku 4.5 API?

As of Oct 4, 2026, QiHang has the lowest Claude Haiku 4.5 output price at $0.71 per 1M tokens, and QiHang has the lowest input price at $0.14 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Claude Haiku 4.5 cost on Anthropic?

Anthropic charges $1 per 1M input tokens and $5 per 1M output tokens for Claude Haiku 4.5.

### How many providers offer Claude Haiku 4.5?

47 providers list Claude Haiku 4.5 on Sovyron; 57 of them sell it at a metered per-token price.

### Is Claude Haiku 4.5 free?

No provider in the Sovyron catalog lists a free tier for Claude Haiku 4.5.

### Is Claude Haiku 4.5 included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Claude Haiku 4.5?

Claude Haiku 4.5 supports a 200k-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/claude-haiku-4-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Opus 4.7 API prices

Claude Opus 4.7 (claude-opus) — 1.0M context, 128k max output.
51 metered per-token offers from 46 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Poe | $4.3 | $21 | $0.43 | 1.0M |
| GMI Cloud | $4.5 | $22.5 | $0.45 | 410k |
| 302.AI | $5 | $25 | $0.5 | 1.0M |
| Abacus | $5 | $25 | — | 1.0M |
| AIHubMix | $5 | $25 | $0.5 | 1.0M |
| Amazon Bedrock | $5 | $25 | $0.5 | 1.0M |
| Amazon Bedrock (global) | $5 | $25 | $0.5 | 1.0M |
| Anthropic | $5 | $25 | $0.5 | 1.0M |
| Auriko | $5 | $25 | $0.5 | 1.0M |
| Azure | $5 | $25 | $0.5 | 1.0M |
| Azure Cognitive Services | $5 | $25 | $0.5 | 1.0M |
| Cloudflare AI Gateway | $5 | $25 | $0.5 | 1.0M |
| CrossModel | $5 | $25 | $0.5 | 1.0M |
| Databricks | $5 | $25 | $0.5 | 1.0M |
| DigitalOcean | $5 | $25 | $0.5 | 200k |
| Eden AI | $5 | $25 | $0.5 | 1.0M |
| FreeModel | $5 | $25 | $0.5 | 1.0M |
| FrogBot | $5 | $25 | $0.5 | 200k |
| Vertex | $5 | $25 | $0.5 | 1.0M |
| Vertex (Anthropic) | $5 | $25 | $0.5 | 1.0M |
| HPC-AI | $5 | $25 | $0.5 | 1.0M |
| Impossibl | $5 | $25 | $0.5 | 1.0M |
| Kilo Gateway | $5 | $25 | $0.5 | 1.0M |
| DevPass (LLM Gateway) | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| Merge Gateway | $5 | $25 | $0.5 | 1.0M |
| NanoGPT | $5 | $25 | $0.5 | 1.0M |
| NEAR AI Cloud | $5 | $25 | $0.5 | 1.0M |
| Neon | $5 | $25 | $0.5 | 1.0M |
| Ofox | $5 | $25 | $0.5 | 1.0M |
| OpenCode Zen | $5 | $25 | $0.5 | 1.0M |
| OpenRouter | $5 | $25 | $0.5 | 1.0M |
| OrcaRouter | $5 | $25 | $0.5 | 1.0M |
| Perplexity Agent | $5 | $25 | $0.5 | 1.0M |
| Pioneer | $5 | $25 | $0.5 | 1.0M |
| Requesty | $5 | $25 | $0.5 | 1.0M |
| SAP AI Core | $5 | $25 | $0.5 | 1.0M |
| Tempr Gateway | $5 | $25 | $0.5 | 1.0M |
| Vercel AI Gateway | $5 | $25 | $0.5 | 1.0M |
| ZenMux | $5 | $25 | $0.5 | 1.0M |
| Cortecs | $5.437 | $27.186 | $0.544 | 1.0M |
| Amazon Bedrock (au) | $5.5 | $27.5 | $0.55 | 1.0M |
| Amazon Bedrock (eu) | $5.5 | $27.5 | $0.55 | 1.0M |
| Amazon Bedrock (jp) | $5.5 | $27.5 | $0.55 | 1.0M |
| Amazon Bedrock (us) | $5.5 | $27.5 | $0.55 | 1.0M |
| Opper | $5.5 | $27.5 | $0.55 | 1.0M |
| Requesty (eu) | $5.5 | $27.5 | $0.55 | 1.0M |
| Venice AI | $6 | $30 | $0.6 | 1.0M |

## Summary

- Cheapest input: $4.3 per 1M tokens (Poe)
- Cheapest output: $21 per 1M tokens (Poe)
- First-party: $25 per 1M output tokens (Anthropic)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-04-16
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Opus 4.7 API?

As of Oct 4, 2026, Poe has the lowest Claude Opus 4.7 output price at $21 per 1M tokens, and Poe has the lowest input price at $4.3 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Claude Opus 4.7 cost on Anthropic?

Anthropic charges $5 per 1M input tokens and $25 per 1M output tokens for Claude Opus 4.7.

### How many providers offer Claude Opus 4.7?

46 providers list Claude Opus 4.7 on Sovyron; 51 of them sell it at a metered per-token price.

### Is Claude Opus 4.7 free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is Claude Opus 4.7 included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Claude Opus 4.7?

Claude Opus 4.7 supports a 1.0M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/claude-opus-4-7/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Opus 4.8 API prices

Claude Opus 4.8 (claude-opus) — 1.0M context, 128k max output.
51 metered per-token offers from 47 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| UnoRouter | $0.425 | $2.125 | — | 1.0M |
| Xpersona | $1.5 | $9.25 | $0.15 | 200k |
| Poe | $4.2929 | $21.4646 | — | 1.0M |
| 302.AI | $5 | $25 | — | 1.0M |
| Abacus | $5 | $25 | — | 1.0M |
| AIHubMix | $5 | $25 | $0.5 | 200k |
| AIHubMix | $5 | $25 | $0.5 | 200k |
| Amazon Bedrock | $5 | $25 | $0.5 | 1.0M |
| Amazon Bedrock (global) | $5 | $25 | $0.5 | 1.0M |
| Anthropic | $5 | $25 | $0.5 | 1.0M |
| Azure | $5 | $25 | $0.5 | 1.0M |
| Azure Cognitive Services | $5 | $25 | $0.5 | 1.0M |
| Cloudflare AI Gateway | $5 | $25 | $0.5 | 1.0M |
| CrossModel | $5 | $25 | $0.5 | 1.0M |
| DaoXE | $5 | $25 | $0.5 | 1.0M |
| DigitalOcean | $5 | $25 | $0.5 | 1.0M |
| Eden AI | $5 | $25 | $0.5 | 1.0M |
| FastRouter | $5 | $25 | — | 1.0M |
| FreeModel | $5 | $25 | $0.5 | 1.0M |
| GMI Cloud | $5 | $25 | $0.5 | 1.0M |
| Vertex | $5 | $25 | $0.5 | 1.0M |
| Vertex (Anthropic) | $5 | $25 | $0.5 | 1.0M |
| Impossibl | $5 | $25 | $0.5 | 1.0M |
| Kilo Gateway | $5 | $25 | $0.5 | 1.0M |
| DevPass (LLM Gateway) | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| Merge Gateway | $5 | $25 | $0.5 | 1.0M |
| Modelis | $5 | $25 | — | 1.0M |
| NanoGPT | $5 | $25 | $0.5 | 1.0M |
| Neon | $5 | $25 | $0.5 | 1.0M |
| Ofox | $5 | $25 | $0.5 | 1.0M |
| OpenCode Zen | $5 | $25 | $0.5 | 1.0M |
| OpenRouter | $5 | $25 | $0.5 | 1.0M |
| Opper | $5 | $25 | $0.5 | 1.0M |
| OrcaRouter | $5 | $25 | $0.5 | 1.0M |
| Pioneer | $5 | $25 | $0.5 | 1.0M |
| Requesty | $5 | $25 | $0.5 | 1.0M |
| routing.run | $5 | $25 | — | 1.0M |
| SAP AI Core | $5 | $25 | $0.5 | 1.0M |
| Tempr Gateway | $5 | $25 | $0.5 | 1.0M |
| Vercel AI Gateway | $5 | $25 | $0.5 | 1.0M |
| ZenMux | $5 | $25 | $0.5 | 1.0M |
| Cortecs | $5.437 | $27.186 | $0.544 | 1.0M |
| Amazon Bedrock (au) | $5.5 | $27.5 | $0.55 | 1.0M |
| Amazon Bedrock (eu) | $5.5 | $27.5 | $0.55 | 1.0M |
| Amazon Bedrock (jp) | $5.5 | $27.5 | $0.55 | 1.0M |
| Amazon Bedrock (us) | $5.5 | $27.5 | $0.55 | 1.0M |
| Requesty (eu) | $5.5 | $27.5 | $0.55 | 1.0M |
| Venice AI | $6 | $30 | $0.6 | 1.0M |

## Summary

- Cheapest input: $0.425 per 1M tokens (UnoRouter)
- Cheapest output: $2.125 per 1M tokens (UnoRouter)
- First-party: $25 per 1M output tokens (Anthropic)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-05-28
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Opus 4.8 API?

As of Oct 4, 2026, UnoRouter has the lowest Claude Opus 4.8 output price at $2.125 per 1M tokens, and UnoRouter has the lowest input price at $0.425 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Claude Opus 4.8 cost on Anthropic?

Anthropic charges $5 per 1M input tokens and $25 per 1M output tokens for Claude Opus 4.8.

### How many providers offer Claude Opus 4.8?

47 providers list Claude Opus 4.8 on Sovyron; 51 of them sell it at a metered per-token price.

### Is Claude Opus 4.8 free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is Claude Opus 4.8 included in a subscription plan?

Yes. 4 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Claude Opus 4.8?

Claude Opus 4.8 supports a 1.0M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/claude-opus-4-8/
Full dataset: https://sovyron.com/data/catalog.json

---

# DeepSeek V4 Flash 0731 API prices

DeepSeek V4 Flash 0731 (deepseek-flash) — 1.0M context, 1.0M max output.
51 metered per-token offers from 44 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Merge Gateway | $0.035 | $0.07 | $0.007 | 1.0M |
| engy | $0.045 | $0.09 | $0.009 | 1.0M |
| NanoGPT | $0.05 | $0.16 | $0.013 | 1.0M |
| NanoGPT | $0.05 | $0.16 | $0.013 | 1.0M |
| Deep Infra | $0.06 | $0.18 | $0.015 | 1.0M |
| Eden AI | $0.06 | $0.18 | $0.015 | 1.0M |
| Vercel AI Gateway | $0.076 | $0.153 | $0.014 | 1.0M |
| Ambient | $0.08 | $0.18 | $0.016 | 1.0M |
| Cortecs | $0.09 | $0.17 | $0.014 | 1.0M |
| Vultr | $0.1 | $0.25 | — | 1.0M |
| Bothub | $0.1 | $0.28 | — | 1.0M |
| Melious | $0.1159 | $0.2898 | $0.0232 | 1.0M |
| Baseten | $0.13 | $0.26 | $0.028 | 1.0M |
| Perplexity Agent | $0.13 | $0.26 | $0.028 | 1.0M |
| RunInfra | $0.13 | $0.27 | $0.01 | 1.0M |
| Inceptron | $0.13 | $0.28 | $0.03 | 1.0M |
| CoreWeave | $0.13 | $0.28 | $0.07 | 262k |
| OpenReason | $0.1371 | $0.2743 | — | 1.0M |
| AMD | $0.14 | $0.28 | $0.0028 | 1.0M |
| DigitalOcean | $0.14 | $0.28 | $0.028 | 1.0M |
| Eden AI | $0.14 | $0.28 | $0.014 | 1.0M |
| Eden AI | $0.14 | $0.28 | $0.14 | 1.0M |
| Eden AI | $0.14 | $0.28 | $0.03 | 1.0M |
| Hugging Face | $0.14 | $0.28 | — | 1.0M |
| Nebius Token Factory | $0.14 | $0.28 | $0.14 | 1.0M |
| Together AI | $0.14 | $0.28 | $0.03 | 1.0M |
| AIHubMix | $0.142 | $0.284 | $0.0284 | 1.0M |
| OrcaRouter | $0.147 | $0.295 | $0.02 | 1.0M |
| Venice AI | $0.175 | $0.35 | $0.035 | 1.0M |
| GreenPT | $0.1596 | $0.399 | $0.0456 | 1.0M |
| Alibaba | $0.2 | $0.4 | $0.04 | 1.0M |
| Eden AI | $0.25 | $0.3 | $0.0625 | 1.0M |
| TensorX | $0.25 | $0.3 | $0.06 | 1.0M |
| AKI.IO | $0.2 | $0.5 | $0.1 | 1.0M |
| Eden AI | $0.22 | $0.66 | $0.022 | 1.0M |
| Ollama Cloud | $0.22 | $0.66 | $0.007 | 1.0M |
| SiliconFlow | $0.22 | $0.66 | $0.014 | 1.0M |
| OpenRouter | $0.0152 | $1.28 | $0.0152 | 1.0M |
| Merge Gateway | $0.28 | $0.56 | $0.07 | 1.0M |
| Requesty | $0.28 | $0.56 | $0.07 | 1.0M |
| Requesty (eu) | $0.28 | $0.56 | $0.07 | 1.0M |
| Ofox | $0.308 | $0.924 | $0.0098 | 1.0M |
| IteraCompute | $0.34 | $1.05 | $0.035 | 970k |
| Eden AI | $0.449 | $0.898 | $0.0898 | 256k |
| Scaleway | $0.468 | $0.936 | $0.0936 | 256k |
| EmpirioLabs AI | $0.424 | $1.272 | $0.424 | 1.0M |
| Cloudflare Workers AI | $0.44 | $1.32 | $0.014 | 1.0M |
| Eden AI | $0.44 | $1.32 | $0.014 | 1.0M |
| Charm Hyper | $0.44 | $1.32 | $0.044 | 1.0M |
| Kilo Gateway | $0.44 | $1.32 | $0.028 | 1.0M |
| Volcengine Ark | $0.4453 | $1.3359 | $0.0148 | 1.0M |

## Summary

- Cheapest input: $0.0152 per 1M tokens (OpenRouter)
- Cheapest output: $0.07 per 1M tokens (Merge Gateway)
- First-party: $0.4 per 1M output tokens (Alibaba)
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China), SCNet Token Plan
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China), SCNet Token Plan
- Released: 2026-07-31
- Inputs: text

## FAQ

### What is the cheapest DeepSeek V4 Flash 0731 API?

As of Oct 4, 2026, Merge Gateway has the lowest DeepSeek V4 Flash 0731 output price at $0.07 per 1M tokens, and OpenRouter has the lowest input price at $0.0152 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does DeepSeek V4 Flash 0731 cost on Alibaba?

Alibaba charges $0.2 per 1M input tokens and $0.4 per 1M output tokens for DeepSeek V4 Flash 0731.

### How many providers offer DeepSeek V4 Flash 0731?

44 providers list DeepSeek V4 Flash 0731 on Sovyron; 51 of them sell it at a metered per-token price.

### Is DeepSeek V4 Flash 0731 free?

No provider in the Sovyron catalog lists a free tier for DeepSeek V4 Flash 0731.

### Is DeepSeek V4 Flash 0731 included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 supports a 1.0M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/deepseek-v4-flash-0731/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Opus 4.6 API prices

Claude Opus 4.6 (claude-opus) — 1.0M context, 128k max output.
47 metered per-token offers from 42 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Poe | $4.3 | $21 | $0.43 | 983k |
| Abacus | $5 | $25 | — | 1.0M |
| AIHubMix | $5 | $25 | $0.5 | 1.0M |
| Amazon Bedrock (global) | $5 | $25 | $0.5 | 1.0M |
| Anthropic | $5 | $25 | $0.5 | 1.0M |
| Auriko | $5 | $25 | $0.5 | 1.0M |
| Azure | $5 | $25 | $0.5 | 1.0M |
| Azure Cognitive Services | $5 | $25 | $0.5 | 1.0M |
| Cloudflare AI Gateway | $5 | $25 | $0.5 | 1.0M |
| Databricks | $5 | $25 | $0.5 | 1.0M |
| DigitalOcean | $5 | $25 | $0.5 | 200k |
| Eden AI | $5 | $25 | $0.5 | 1.0M |
| FreeModel | $5 | $25 | $0.5 | 1.0M |
| FrogBot | $5 | $25 | $0.5 | 200k |
| GMI Cloud | $5 | $25 | $0.5 | 410k |
| Vertex | $5 | $25 | $0.5 | 1.0M |
| Vertex (Anthropic) | $5 | $25 | $0.5 | 1.0M |
| Impossibl | $5 | $25 | $0.5 | 1.0M |
| Jiekou.AI | $5 | $25 | — | 1.0M |
| Kilo Gateway | $5 | $25 | $0.5 | 1.0M |
| DevPass (LLM Gateway) | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| Merge Gateway | $5 | $25 | $0.5 | 1.0M |
| NanoGPT | $5 | $25 | $0.5 | 1.0M |
| NEAR AI Cloud | $5 | $25 | $0.5 | 200k |
| Neon | $5 | $25 | $0.5 | 1.0M |
| Ofox | $5 | $25 | $0.5 | 1.0M |
| OpenCode Zen | $5 | $25 | $0.5 | 1.0M |
| OpenRouter | $5 | $25 | $0.5 | 1.0M |
| Opper | $5 | $25 | $0.5 | 1.0M |
| OrcaRouter | $5 | $25 | $0.5 | 1.0M |
| Perplexity Agent | $5 | $25 | $0.5 | 200k |
| Pioneer | $5 | $25 | $0.5 | 1.0M |
| Requesty | $5 | $25 | $0.5 | 1.0M |
| SAP AI Core | $5 | $25 | $0.5 | 1.0M |
| Tempr Gateway | $5 | $25 | $0.5 | 1.0M |
| Vercel AI Gateway | $5 | $25 | $0.5 | 1.0M |
| ZenMux | $5 | $25 | $0.5 | 1.0M |
| Cortecs | $5.313 | $26.561 | $0.531 | 1.0M |
| Amazon Bedrock | $5.5 | $27.5 | $0.55 | 1.0M |
| Amazon Bedrock (eu) | $5.5 | $27.5 | $0.55 | 1.0M |
| Amazon Bedrock (us) | $5.5 | $27.5 | $0.55 | 1.0M |
| Requesty (eu) | $5.5 | $27.5 | $0.55 | 1.0M |
| Venice AI | $6 | $30 | $0.6 | 1.0M |

## Summary

- Cheapest input: $4.3 per 1M tokens (Poe)
- Cheapest output: $21 per 1M tokens (Poe)
- First-party: $25 per 1M output tokens (Anthropic)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-02-05
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Opus 4.6 API?

As of Oct 4, 2026, Poe has the lowest Claude Opus 4.6 output price at $21 per 1M tokens, and Poe has the lowest input price at $4.3 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Claude Opus 4.6 cost on Anthropic?

Anthropic charges $5 per 1M input tokens and $25 per 1M output tokens for Claude Opus 4.6.

### How many providers offer Claude Opus 4.6?

42 providers list Claude Opus 4.6 on Sovyron; 47 of them sell it at a metered per-token price.

### Is Claude Opus 4.6 free?

No provider in the Sovyron catalog lists a free tier for Claude Opus 4.6.

### What is the context window of Claude Opus 4.6?

Claude Opus 4.6 supports a 1.0M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/claude-opus-4-6/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.4 API prices

GPT-5.4 (gpt) — 1.1M context, 131k max output.
42 metered per-token offers from 44 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Xpersona | $0.75 | $6 | $0.075 | 1.1M |
| UnoRouter | $1.8 | $10.8 | — | 1.1M |
| Ofox | $2 | $12 | $0.2 | 1.1M |
| Poe | $2.2 | $14 | $0.22 | 1.1M |
| 302.AI | $2.5 | $15 | $0.25 | 1.1M |
| Abacus | $2.5 | $15 | $0.25 | 400k |
| AI-ROUTER | $2.5 | $15 | $0.25 | 1.1M |
| AIHubMix | $2.5 | $15 | $0.25 | 1.1M |
| Azure | $2.5 | $15 | $0.25 | 1.1M |
| Azure Cognitive Services | $2.5 | $15 | $0.25 | 1.1M |
| Cloudflare AI Gateway | $2.5 | $15 | $0.25 | 1.0M |
| CrossModel | $2.5 | $15 | $0.25 | 1.1M |
| DaoXE | $2.5 | $15 | $0.25 | 1.1M |
| Databricks | $2.5 | $15 | $0.25 | 1.1M |
| DigitalOcean | $2.5 | $15 | $0.25 | 400k |
| Eden AI | $2.5 | $15 | $0.25 | 1.1M |
| FreeModel | $2.5 | $15 | $0.25 | 1.1M |
| Impossibl | $2.5 | $15 | $0.25 | 1.1M |
| Kilo Gateway | $2.5 | $15 | $0.25 | 1.1M |
| DevPass (LLM Gateway) | $2.5 | $15 | $0.25 | 1.1M |
| LLM Gateway | $2.5 | $15 | $0.25 | 1.1M |
| LLM Gateway | $2.5 | $15 | $0.25 | 1.1M |
| Merge Gateway | $2.5 | $15 | $0.25 | 1.1M |
| NanoGPT | $2.5 | $15 | $0.25 | 1.1M |
| NEAR AI Cloud | $2.5 | $15 | $0.25 | 1.1M |
| Neon | $2.5 | $15 | $0.25 | 1.1M |
| OpenAI | $2.5 | $15 | $0.25 | 1.1M |
| OpenCode Zen | $2.5 | $15 | $0.25 | 1.1M |
| OpenRouter | $2.5 | $15 | $0.25 | 1.1M |
| Opper | $2.5 | $15 | $0.25 | 1.1M |
| OrcaRouter | $2.5 | $15 | $0.25 | 1.1M |
| Perplexity Agent | $2.5 | $15 | $0.25 | 1.1M |
| Pioneer | $2.5 | $15 | $0.25 | 1.1M |
| SAP AI Core | $2.5 | $15 | $0.25 | 1.1M |
| Vercel AI Gateway | $2.5 | $15 | $0.25 | 1.1M |
| Vivgrid | $2.5 | $15 | $0.25 | 400k |
| Cortecs | $2.898 | $15.453 | $0.242 | 1.1M |
| Amazon Bedrock | $2.75 | $16.5 | $0.275 | 1.0M |
| Requesty | $2.75 | $16.5 | $0.275 | 1.1M |
| Requesty (eu) | $2.75 | $16.5 | $0.275 | 1.1M |
| Venice AI | $3.13 | $18.8 | $0.313 | 1.0M |
| ZenMux | $3.75 | $18.75 | — | 1.1M |

## Summary

- Cheapest input: $0.75 per 1M tokens (Xpersona)
- Cheapest output: $6 per 1M tokens (Xpersona)
- First-party: $15 per 1M output tokens (OpenAI)
- Free offers: UnoRouter
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-03-05
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.4 API?

As of Oct 4, 2026, Xpersona has the lowest GPT-5.4 output price at $6 per 1M tokens, and Xpersona has the lowest input price at $0.75 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5.4 cost on OpenAI?

OpenAI charges $2.5 per 1M input tokens and $15 per 1M output tokens for GPT-5.4.

### How many providers offer GPT-5.4?

44 providers list GPT-5.4 on Sovyron; 42 of them sell it at a metered per-token price.

### Is GPT-5.4 free?

1 provider(s) list a free-tier offer: UnoRouter. Free tiers usually have rate limits.

### Is GPT-5.4 included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of GPT-5.4?

GPT-5.4 supports a 1.1M-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/gpt-5-4/
Full dataset: https://sovyron.com/data/catalog.json

---

# Qwen3.8 27B API prices

Qwen3.8 27B (qwen) — 1.1M context, 500k max output.
40 metered per-token offers from 40 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| engy | $0.045 | $0.32 | $0.015 | 1.0M |
| DevPass (LLM Gateway) | $0.08 | $0.35 | $0.05 | 262k |
| Cortecs | $0.1 | $0.4 | $0.04 | 1.0M |
| RunInfra | $0.1 | $0.4 | $0.01 | 262k |
| EmpirioLabs AI | $0.17 | $0.5 | $0.08 | 262k |
| NanoGPT | $0.15 | $0.7 | $0.04 | 262k |
| Vultr | $0.15 | $1 | — | 262k |
| CrofAI | $0.2 | $1.5 | $0.03 | 262k |
| LLM Tech | $0.25 | $2.09 | $0.04 | 262k |
| AKI.IO | $0.3 | $2.2 | $0.1 | 262k |
| Deep Infra | $0.2 | $2.5 | $0.05 | 262k |
| Ofox | $0.5 | $1.71 | $0.043 | 1.1M |
| Kosmik Compute | $0.35 | $2.2 | $0.09 | 262k |
| OrcaRouter | $0.33 | $2.4 | — | 262k |
| IteraCompute | $0.3 | $2.5 | $0.03 | 328k |
| TensorX | $0.4 | $2.4 | $0.1 | 262k |
| Kilo Gateway | $0.425 | $2.55 | $0.085 | 1.0M |
| OpenRouter | $0.425 | $2.55 | $0.085 | 1.0M |
| Ambient | $0.32 | $3.2 | $0.16 | 33k |
| Regolo AI | $0.58 | $2.42 | — | 120k |
| ai& | $0.4 | $3 | $0.2 | 262k |
| Hugging Face | $0.4 | $3 | — | 262k |
| CoreWeave | $0.4 | $3 | $0.15 | 262k |
| LLM Gateway | $0.42 | $3 | $0.085 | 1.0M |
| Nebius Token Factory | $0.45 | $3 | $0.45 | 262k |
| Cerebras | $0.99 | $1.49 | $0.99 | 131k |
| Tempr Gateway | $0.99 | $1.49 | — | 131k |
| Eden AI | $0.5 | $3 | $0.1 | 1.0M |
| Charm Hyper | $0.5 | $3 | $0.1 | 1.0M |
| Vercel AI Gateway | $0.5 | $3 | $0.1 | 1.0M |
| Cloudflare Workers AI | $0.45 | $3.2 | $0.05 | 262k |
| Neuralwatt | $0.45 | $3.2 | $0.25 | 262k |
| Ofox | $0.45 | $3.2 | $0.05 | 1.1M |
| OVHcloud AI Endpoints | $0.47 | $3.19 | — | 262k |
| Opper | $0.5811 | $3 | — | 262k |
| Berget.AI | $0.46 | $3.48 | — | 262k |
| Scaleway | $0.684 | $3.762 | $0.137 | 262k |
| evroc | $0.87 | $3.5 | — | 262k |
| Groq | $0.8 | $4 | — | 131k |
| Tempr Gateway | $0.8 | $4 | — | 131k |

## Summary

- Cheapest input: $0.045 per 1M tokens (engy)
- Cheapest output: $0.32 per 1M tokens (engy)
- First-party: not listed separately
- Free offers: AMD, Hetzner, OpenRouter
- Subscription plans (not per-token): none
- Released: 2026-08-14
- Inputs: image, pdf, text, video

## FAQ

### What is the cheapest Qwen3.8 27B API?

As of Oct 4, 2026, engy has the lowest Qwen3.8 27B output price at $0.32 per 1M tokens, and engy has the lowest input price at $0.045 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Qwen3.8 27B?

40 providers list Qwen3.8 27B on Sovyron; 40 of them sell it at a metered per-token price.

### Is Qwen3.8 27B free?

3 provider(s) list a free-tier offer: AMD, Hetzner, OpenRouter. Free tiers usually have rate limits.

### What is the context window of Qwen3.8 27B?

Qwen3.8 27B supports a 1.1M-token context window and up to 500k output tokens.

HTML page: https://sovyron.com/models/qwen3-8-27b/
Full dataset: https://sovyron.com/data/catalog.json

---

# MiniMax-M2.7 API prices

MiniMax-M2.7 (minimax) — 262k context, 197k max output.
39 metered per-token offers from 41 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| DevPass (LLM Gateway) | $0.08 | $0.32 | $0.017 | 205k |
| EmpirioLabs AI | $0.15 | $0.6 | $0.03 | 200k |
| OpenRouter | $0.21 | $0.84 | $0.042 | 205k |
| Pioneer | $0.279 | $1.2 | $0.279 | 205k |
| 302.AI | $0.3 | $1.2 | — | 205k |
| Abacus | $0.3 | $1.2 | — | 205k |
| AIHubMix | $0.3 | $1.2 | $0.06 | 205k |
| Alibaba (China) | $0.3 | $1.2 | $0.06 | 205k |
| Auriko | $0.3 | $1.2 | — | 205k |
| Eden AI | $0.3 | $1.2 | $0.06 | 205k |
| FastRouter | $0.3 | $1.2 | — | 205k |
| FrogBot | $0.3 | $1.2 | $0.06 | 192k |
| GMI Cloud | $0.3 | $1.2 | $0.06 | 197k |
| Hugging Face | $0.3 | $1.2 | $0.06 | 205k |
| Kilo Gateway | $0.3 | $1.2 | $0.06 | 197k |
| LLM Gateway | $0.3 | $1.2 | $0.06 | 205k |
| LLM Gateway | $0.3 | $1.2 | $0.06 | 205k |
| LLM Gateway | $0.3 | $1.2 | $0.06 | 200k |
| Merge Gateway | $0.3 | $1.2 | $0.06 | 205k |
| MiniMax (minimax.io) | $0.3 | $1.2 | $0.06 | 205k |
| MiniMax (minimax.cn) | $0.3 | $1.2 | $0.06 | 205k |
| NovitaAI | $0.3 | $1.2 | $0.06 | 205k |
| Ofox | $0.3 | $1.2 | $0.06 | 205k |
| Ollama Cloud | $0.3 | $1.2 | $0.06 | 197k |
| OpenCode Zen | $0.3 | $1.2 | $0.06 | 205k |
| OpenCode Go | $0.3 | $1.2 | $0.06 | 205k |
| OrcaRouter | $0.3 | $1.2 | $0.06 | 205k |
| Requesty | $0.3 | $1.2 | $0.06 | 200k |
| Tempr Gateway | $0.3 | $1.2 | $0.06 | 205k |
| Together AI | $0.3 | $1.2 | $0.06 | 197k |
| Vercel AI Gateway | $0.3 | $1.2 | $0.06 | 205k |
| ZenMux | $0.3055 | $1.2219 | — | 205k |
| NanoGPT | $0.315 | $1.26 | $0.1575 | 205k |
| CrossModel | $0.33 | $1.32 | $0.066 | 205k |
| Venice AI | $0.375 | $1.5 | $0.0688 | 198k |
| SCX.ai | $0.48 | $1.79 | $0.05 | 197k |
| Charm Hyper | $0.484 | $1.852 | $0.242 | 262k |
| Opper | $0.6973 | $2.7893 | — | 197k |
| UnoRouter | $0.819 | $3.276 | — | 205k |

## Summary

- Cheapest input: $0.08 per 1M tokens (DevPass (LLM Gateway))
- Cheapest output: $0.32 per 1M tokens (DevPass (LLM Gateway))
- First-party: $1.2 per 1M output tokens (MiniMax (minimax.io))
- Free offers: Kenari, MiniMax Token Plan (minimax.cn), MiniMax Token Plan (minimax.io), SCNet Token Plan, UnoRouter
- Subscription plans (not per-token): MiniMax Token Plan (minimax.cn), MiniMax Token Plan (minimax.io), SCNet Token Plan
- Released: 2026-03-18
- Inputs: text

## FAQ

### What is the cheapest MiniMax-M2.7 API?

As of Oct 4, 2026, DevPass (LLM Gateway) has the lowest MiniMax-M2.7 output price at $0.32 per 1M tokens, and DevPass (LLM Gateway) has the lowest input price at $0.08 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does MiniMax-M2.7 cost on MiniMax (minimax.io)?

MiniMax (minimax.io) charges $0.3 per 1M input tokens and $1.2 per 1M output tokens for MiniMax-M2.7.

### How many providers offer MiniMax-M2.7?

41 providers list MiniMax-M2.7 on Sovyron; 39 of them sell it at a metered per-token price.

### Is MiniMax-M2.7 free?

2 provider(s) list a free-tier offer: Kenari, UnoRouter. Free tiers usually have rate limits.

### Is MiniMax-M2.7 included in a subscription plan?

Yes. 4 flat-rate plan(s) include it; the cheapest is OpenCode OpenCode Go at $10/month.

### What is the context window of MiniMax-M2.7?

MiniMax-M2.7 supports a 262k-token context window and up to 197k output tokens.

HTML page: https://sovyron.com/models/minimax-m2-7/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Opus 4.5 API prices

Claude Opus 4.5 (claude-opus) — 200k context, 200k max output.
45 metered per-token offers from 38 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| QiHang | $0.71 | $3.57 | — | 200k |
| Poe | $4.3 | $21 | $0.43 | 197k |
| Abacus | $5 | $25 | — | 200k |
| AIHubMix | $5 | $25 | $0.5 | 200k |
| Amazon Bedrock | $5 | $25 | $0.5 | 200k |
| Amazon Bedrock (global) | $5 | $25 | $0.5 | 200k |
| Anthropic | $5 | $25 | $0.5 | 200k |
| Anthropic | $5 | $25 | $0.5 | 200k |
| Azure | $5 | $25 | $0.5 | 200k |
| Azure Cognitive Services | $5 | $25 | $0.5 | 200k |
| Cloudflare AI Gateway | $5 | $25 | $0.5 | 200k |
| Databricks | $5 | $25 | $0.5 | 200k |
| DigitalOcean | $5 | $25 | $0.5 | 200k |
| Eden AI | $5 | $25 | $0.5 | 200k |
| Eden AI | $5 | $25 | $0.5 | 200k |
| Vertex | $5 | $25 | $0.5 | 200k |
| Vertex (Anthropic) | $5 | $25 | $0.5 | 200k |
| Helicone | $5 | $25 | $0.5 | 200k |
| Impossibl | $5 | $25 | $0.5 | 200k |
| Kilo Gateway | $5 | $25 | $0.5 | 200k |
| DevPass (LLM Gateway) | $5 | $25 | $0.5 | 200k |
| LLM Gateway | $5 | $25 | $0.5 | 200k |
| LLM Gateway | $5 | $25 | $0.5 | 200k |
| LLM Gateway | $5 | $25 | $0.5 | 200k |
| Merge Gateway | $5 | $25 | $0.5 | 200k |
| NanoGPT | $5 | $25 | $0.5 | 200k |
| Neon | $5 | $25 | $0.5 | 200k |
| Ofox | $5 | $25 | $0.5 | 200k |
| OpenCode Zen | $5 | $25 | $0.5 | 200k |
| OpenRouter | $5 | $25 | $0.5 | 200k |
| Opper | $5 | $25 | $0.5 | 200k |
| OrcaRouter | $5 | $25 | $0.5 | 200k |
| Perplexity Agent | $5 | $25 | $0.5 | 200k |
| Pioneer | $5 | $25 | $0.5 | 200k |
| Requesty | $5 | $25 | $0.5 | 200k |
| SAP AI Core | $5 | $25 | $0.5 | 200k |
| Tempr Gateway | $5 | $25 | $0.5 | 200k |
| Tempr Gateway | $5 | $25 | $0.5 | 200k |
| Vercel AI Gateway | $5 | $25 | $0.5 | 200k |
| ZenMux | $5 | $25 | $0.5 | 200k |
| Cortecs | $5.313 | $26.568 | $0.531 | 200k |
| Amazon Bedrock (eu) | $5.5 | $27.5 | $0.55 | 200k |
| Amazon Bedrock (us) | $5.5 | $27.5 | $0.55 | 200k |
| Requesty | $5.5 | $27.5 | $0.55 | 200k |
| Venice AI | $6 | $30 | $0.6 | 198k |

## Summary

- Cheapest input: $0.71 per 1M tokens (QiHang)
- Cheapest output: $3.57 per 1M tokens (QiHang)
- First-party: $25 per 1M output tokens (Anthropic)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-11-24
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Opus 4.5 API?

As of Oct 4, 2026, QiHang has the lowest Claude Opus 4.5 output price at $3.57 per 1M tokens, and QiHang has the lowest input price at $0.71 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Claude Opus 4.5 cost on Anthropic?

Anthropic charges $5 per 1M input tokens and $25 per 1M output tokens for Claude Opus 4.5.

### How many providers offer Claude Opus 4.5?

38 providers list Claude Opus 4.5 on Sovyron; 45 of them sell it at a metered per-token price.

### Is Claude Opus 4.5 free?

No provider in the Sovyron catalog lists a free tier for Claude Opus 4.5.

### What is the context window of Claude Opus 4.5?

Claude Opus 4.5 supports a 200k-token context window and up to 200k output tokens.

HTML page: https://sovyron.com/models/claude-opus-4-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Sonnet 4.5 API prices

Claude Sonnet 4.5 (claude-sonnet) — 1.0M context, 64k max output.
51 metered per-token offers from 39 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| QiHang | $0.43 | $2.14 | — | 200k |
| Poe | $2.6 | $13 | $0.26 | 983k |
| Cortecs | $2.989 | $14.945 | $0.326 | 200k |
| Abacus | $3 | $15 | — | 200k |
| Amazon Bedrock | $3 | $15 | $0.3 | 200k |
| Amazon Bedrock (global) | $3 | $15 | $0.3 | 200k |
| Anthropic | $3 | $15 | $0.3 | 1.0M |
| Anthropic | $3 | $15 | $0.3 | 1.0M |
| Azure | $3 | $15 | $0.3 | 200k |
| Azure Cognitive Services | $3 | $15 | $0.3 | 200k |
| Cloudflare AI Gateway | $3 | $15 | $0.3 | 200k |
| Databricks | $3 | $15 | $0.3 | 200k |
| Databricks | $3 | $15 | $0.3 | 200k |
| DigitalOcean | $3 | $15 | $0.3 | 200k |
| Vertex | $3 | $15 | $0.3 | 200k |
| Vertex (Anthropic) | $3 | $15 | $0.3 | 200k |
| Helicone | $3 | $15 | $0.3 | 200k |
| Helicone | $3 | $15 | $0.3 | 200k |
| Impossibl | $3 | $15 | $0.3 | 200k |
| Kilo Gateway | $3 | $15 | $0.3 | 1.0M |
| DevPass (LLM Gateway) | $3 | $15 | $0.3 | 200k |
| DevPass (LLM Gateway) | $3 | $15 | $0.3 | 200k |
| LLM Gateway | $3 | $15 | $0.3 | 200k |
| LLM Gateway | $3 | $15 | $0.3 | 200k |
| LLM Gateway | $3 | $15 | $0.3 | 200k |
| LLM Gateway | $3 | $15 | $0.3 | 200k |
| LLM Gateway | $3 | $15 | $0.3 | 200k |
| Merge Gateway | $3 | $15 | $0.3 | 200k |
| NanoGPT | $3 | $15 | $0.3 | 200k |
| NEAR AI Cloud | $3 | $15 | $0.3 | 200k |
| Neon | $3 | $15 | $0.3 | 200k |
| Ofox | $3 | $15 | $0.3 | 200k |
| OpenCode Zen | $3 | $15 | $0.3 | 1.0M |
| OpenRouter | $3 | $15 | $0.3 | 1.0M |
| OrcaRouter | $3 | $15 | $0.3 | 1.0M |
| Perplexity Agent | $3 | $15 | $0.3 | 200k |
| Pioneer | $3 | $15 | $0.3 | 1.0M |
| Requesty | $3 | $15 | $0.3 | 1.0M |
| SAP AI Core | $3 | $15 | $0.3 | 200k |
| Tempr Gateway | $3 | $15 | $0.3 | 200k |
| Tempr Gateway | $3 | $15 | $0.3 | 200k |
| Vercel AI Gateway | $3 | $15 | $0.3 | 1.0M |
| ZenMux | $3 | $15 | $0.3 | 1.0M |
| AIHubMix | $3.3 | $16.5 | $0.33 | 1.0M |
| Amazon Bedrock (au) | $3.3 | $16.5 | $0.33 | 200k |
| Amazon Bedrock (eu) | $3.3 | $16.5 | $0.33 | 200k |
| Amazon Bedrock (jp) | $3.3 | $16.5 | $0.33 | 200k |
| Amazon Bedrock (us) | $3.3 | $16.5 | $0.33 | 200k |
| Opper | $3.3 | $16.5 | $0.33 | 200k |
| Requesty | $3.3 | $16.5 | $0.3 | 1.0M |
| Venice AI | $3.75 | $18.75 | $0.375 | 198k |

## Summary

- Cheapest input: $0.43 per 1M tokens (QiHang)
- Cheapest output: $2.14 per 1M tokens (QiHang)
- First-party: $15 per 1M output tokens (Anthropic)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-09-29
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Sonnet 4.5 API?

As of Oct 4, 2026, QiHang has the lowest Claude Sonnet 4.5 output price at $2.14 per 1M tokens, and QiHang has the lowest input price at $0.43 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Claude Sonnet 4.5 cost on Anthropic?

Anthropic charges $3 per 1M input tokens and $15 per 1M output tokens for Claude Sonnet 4.5.

### How many providers offer Claude Sonnet 4.5?

39 providers list Claude Sonnet 4.5 on Sovyron; 51 of them sell it at a metered per-token price.

### Is Claude Sonnet 4.5 free?

No provider in the Sovyron catalog lists a free tier for Claude Sonnet 4.5.

### What is the context window of Claude Sonnet 4.5?

Claude Sonnet 4.5 supports a 1.0M-token context window and up to 64k output tokens.

HTML page: https://sovyron.com/models/claude-sonnet-4-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# GLM-5 API prices

GLM-5 (glm) — 205k context, 203k max output.
40 metered per-token offers from 43 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Vultr | $0.4 | $1.75 | — | 203k |
| GMI Cloud | $0.6 | $1.92 | $0.12 | 203k |
| Kilo Gateway | $0.6 | $1.92 | $0.12 | 198k |
| OpenRouter | $0.6 | $1.92 | $0.12 | 205k |
| NanoGPT | $0.5 | $2.55 | $0.13 | 200k |
| Alibaba (China) | $0.573 | $2.58 | — | 203k |
| LLM Gateway | $0.573 | $2.58 | — | 203k |
| ZenMux | $0.58 | $2.6 | $0.14 | 200k |
| 302.AI | $0.6 | $2.6 | — | 205k |
| DevPass (LLM Gateway) | $0.72 | $2.3 | $0.144 | 203k |
| DInference | $0.75 | $2.4 | — | 200k |
| CrossModel | $0.6 | $3 | $0.16 | 200k |
| Meganova | $0.8 | $2.56 | — | 203k |
| TokenGo | $0.89 | $3.2647 | $0.2226 | 205k |
| Baseten | $0.95 | $3.15 | $0.2 | 203k |
| FastRouter | $0.95 | $3.15 | — | 205k |
| Cortecs | $0.988 | $3.164 | $0.247 | 203k |
| Abacus | $1 | $3.2 | — | 205k |
| Amazon Bedrock | $1 | $3.2 | — | 203k |
| DigitalOcean | $1 | $3.2 | $0.2 | 64k |
| Eden AI | $1 | $3.2 | $0.2 | 203k |
| Hugging Face | $1 | $3.2 | $0.2 | 203k |
| Impossibl | $1 | $3.2 | $0.2 | 205k |
| LLM Gateway | $1 | $3.2 | $0.2 | 203k |
| LLM Gateway | $1 | $3.2 | $0.2 | 200k |
| LLM Gateway | $1 | $3.2 | $0.1 | 203k |
| LLM Gateway | $1 | $3.2 | $0.2 | 203k |
| Merge Gateway | $1 | $3.2 | $0.2 | 200k |
| NovitaAI | $1 | $3.2 | $0.2 | 203k |
| Ofox | $1 | $3.2 | $0.2 | 205k |
| OpenCode Zen | $1 | $3.2 | $0.2 | 205k |
| OrcaRouter | $1 | $3.2 | $0.26 | 205k |
| Poe | $1 | $3.2 | $0.2 | 205k |
| Tempr Gateway | $1 | $3.2 | $0.2 | 205k |
| TensorX | $1 | $3.2 | $0.25 | 203k |
| Venice AI | $1 | $3.2 | $0.2 | 198k |
| Vercel AI Gateway | $1 | $3.2 | — | 203k |
| Z.AI | $1 | $3.2 | $0.2 | 205k |
| Zhipu AI | $1 | $3.2 | $0.2 | 205k |
| Melious | $1.1012 | $3.3617 | $0.2666 | 203k |

## Summary

- Cheapest input: $0.4 per 1M tokens (Vultr)
- Cheapest output: $1.75 per 1M tokens (Vultr)
- First-party: $3.2 per 1M output tokens (Z.AI)
- Free offers: Alibaba Coding Plan, Alibaba Coding Plan (China), Alibaba Token Plan, Alibaba Token Plan (China), SCNet Token Plan, Tencent Coding Plan (China)
- Subscription plans (not per-token): Alibaba Coding Plan, Alibaba Coding Plan (China), Alibaba Token Plan, Alibaba Token Plan (China), SCNet Token Plan, Tencent Coding Plan (China)
- Released: 2026-02-12
- Inputs: text

## FAQ

### What is the cheapest GLM-5 API?

As of Oct 4, 2026, Vultr has the lowest GLM-5 output price at $1.75 per 1M tokens, and Vultr has the lowest input price at $0.4 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GLM-5 cost on Z.AI?

Z.AI charges $1 per 1M input tokens and $3.2 per 1M output tokens for GLM-5.

### How many providers offer GLM-5?

43 providers list GLM-5 on Sovyron; 40 of them sell it at a metered per-token price.

### Is GLM-5 free?

No provider in the Sovyron catalog lists a free tier for GLM-5.

### Is GLM-5 included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of GLM-5?

GLM-5 supports a 205k-token context window and up to 203k output tokens.

HTML page: https://sovyron.com/models/glm-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.6 Luna API prices

GPT-5.6 Luna (gpt-luna) — 1.1M context, 128k max output.
42 metered per-token offers from 39 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Bothub | $0.06 | $0.37 | — | 1.1M |
| 302.AI | $0.2 | $1.2 | — | 1.1M |
| Amazon Bedrock (global) | $0.2 | $1.2 | $0.02 | 1.1M |
| Azure | $0.2 | $1.2 | $0.02 | 1.1M |
| Cloudflare AI Gateway | $0.2 | $1.2 | $0.02 | 1.1M |
| CrossModel | $0.2 | $1.2 | $0.02 | 1.1M |
| DigitalOcean | $0.2 | $1.2 | $0.02 | 1.1M |
| Eden AI | $0.2 | $1.2 | $0.02 | 1.1M |
| Impossibl | $0.2 | $1.2 | $0.02 | 1.1M |
| Kilo Gateway | $0.2 | $1.2 | $0.02 | 1.1M |
| Kilo Gateway | $0.2 | $1.2 | $0.02 | 1.1M |
| DevPass (LLM Gateway) | $0.2 | $1.2 | $0.02 | 1.1M |
| LLM Gateway | $0.2 | $1.2 | $0.02 | 1.1M |
| LLM Gateway | $0.2 | $1.2 | $0.02 | 1.1M |
| Merge Gateway | $0.2 | $1.2 | $0.02 | 1.1M |
| NanoGPT | $0.2 | $1.2 | $0.02 | 1.1M |
| Neon | $0.2 | $1.2 | $0.02 | 1.1M |
| Ofox | $0.2 | $1.2 | $0.02 | 1.1M |
| OpenAI | $0.2 | $1.2 | $0.02 | 1.1M |
| OpenCode Zen | $0.2 | $1.2 | $0.02 | 1.1M |
| OpenCode Go | $0.2 | $1.2 | $0.02 | 1.1M |
| OpenRouter | $0.2 | $1.2 | $0.02 | 1.1M |
| Opper | $0.2 | $1.2 | $0.02 | 1.0M |
| OrcaRouter | $0.2 | $1.2 | $0.02 | 1.1M |
| Requesty | $0.2 | $1.2 | $0.02 | 1.1M |
| Vercel AI Gateway | $0.2 | $1.2 | $0.02 | 1.1M |
| Cortecs | $0.219 | $1.32 | $0.022 | 1.1M |
| Amazon Bedrock (india) | $0.22 | $1.32 | $0.022 | 1.1M |
| Amazon Bedrock | $0.22 | $1.32 | $0.022 | 1.1M |
| Amazon Bedrock (us) | $0.22 | $1.32 | $0.022 | 1.1M |
| Requesty (eu) | $0.22 | $1.32 | $0.022 | 1.1M |
| Venice AI | $0.25 | $1.5 | $0.025 | 1.0M |
| routing.run | $0.7 | $4.2 | — | 1.0M |
| Abacus | $1 | $6 | $0.1 | 1.0M |
| AI-ROUTER | $1 | $6 | $0.1 | 1.1M |
| AIHubMix | $1 | $6 | $0.1 | 1.1M |
| Azure Cognitive Services | $1 | $6 | $0.1 | 1.1M |
| Databricks | $1 | $6 | $0.1 | 400k |
| Pioneer | $1 | $6 | $0.1 | 1.1M |
| SAP AI Core | $1 | $6 | $0.1 | 1.1M |
| Vivgrid | $1 | $6 | $0.1 | 1.1M |
| ZenMux | $1 | $6 | $0.1 | 1.1M |

## Summary

- Cheapest input: $0.06 per 1M tokens (Bothub)
- Cheapest output: $0.37 per 1M tokens (Bothub)
- First-party: $1.2 per 1M output tokens (OpenAI)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-07-09
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.6 Luna API?

As of Oct 4, 2026, Bothub has the lowest GPT-5.6 Luna output price at $0.37 per 1M tokens, and Bothub has the lowest input price at $0.06 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5.6 Luna cost on OpenAI?

OpenAI charges $0.2 per 1M input tokens and $1.2 per 1M output tokens for GPT-5.6 Luna.

### How many providers offer GPT-5.6 Luna?

39 providers list GPT-5.6 Luna on Sovyron; 42 of them sell it at a metered per-token price.

### Is GPT-5.6 Luna free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is GPT-5.6 Luna included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of GPT-5.6 Luna?

GPT-5.6 Luna supports a 1.1M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-6-luna/
Full dataset: https://sovyron.com/data/catalog.json

---

# Kimi K2.5 API prices

Kimi K2.5 (kimi-k2) — 262k context, 262k max output.
39 metered per-token offers from 44 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| NanoGPT | $0.3 | $1.9 | $0.15 | 256k |
| DevPass (LLM Gateway) | $0.405 | $1.98 | $0.225 | 262k |
| Eden AI | $0.45 | $2.25 | $0.07 | 262k |
| OpenRouter | $0.45 | $2.25 | $0.07 | 262k |
| SiliconFlow | $0.45 | $2.25 | $0.07 | 262k |
| Alibaba (China) | $0.574 | $2.411 | — | 262k |
| Meganova | $0.45 | $2.8 | — | 262k |
| DigitalOcean | $0.5 | $2.7 | $0.203 | 262k |
| Cortecs | $0.495 | $2.768 | $0.124 | 262k |
| Auriko | $0.5 | $2.8 | — | 262k |
| Eden AI | $0.5 | $2.8 | $0.125 | 262k |
| TensorX | $0.5 | $2.8 | $0.125 | 262k |
| Melious | $0.5796 | $2.956 | $0.1391 | 262k |
| LLM Gateway | $0.574 | $3.011 | — | 262k |
| ZenMux | $0.58 | $3.02 | $0.1 | 262k |
| Abacus | $0.6 | $3 | — | 262k |
| AIHubMix | $0.6 | $3 | $0.1 | 262k |
| Amazon Bedrock | $0.6 | $3 | — | 262k |
| Azure | $0.6 | $3 | — | 262k |
| Azure Cognitive Services | $0.6 | $3 | — | 262k |
| Baseten | $0.6 | $3 | $0.12 | 262k |
| DaoXE | $0.6 | $3 | $0.1 | 262k |
| Eden AI | $0.6 | $3 | — | 262k |
| FrogBot | $0.6 | $3 | $0.1 | 256k |
| HPC-AI | $0.6 | $3 | $0.1 | 256k |
| Hugging Face | $0.6 | $3 | $0.1 | 262k |
| Jalapeno Cloud | $0.6 | $3 | — | 262k |
| Jiekou.AI | $0.6 | $3 | — | 262k |
| Kilo Gateway | $0.6 | $3 | — | 262k |
| LLM Gateway | $0.6 | $3 | $0.1 | 262k |
| Merge Gateway | $0.6 | $3 | $0.1 | 262k |
| NovitaAI | $0.6 | $3 | $0.1 | 262k |
| Ofox | $0.6 | $3 | $0.1 | 262k |
| OpenCode Zen | $0.6 | $3 | $0.08 | 262k |
| OrcaRouter | $0.6 | $3 | $0.1 | 262k |
| Poe | $0.6 | $3 | $0.1 | 128k |
| Vercel AI Gateway | $0.6 | $3 | — | 256k |
| Venice AI | $0.56 | $3.5 | $0.22 | 256k |
| 302.AI | $0.66 | $3.3 | — | 262k |

## Summary

- Cheapest input: $0.3 per 1M tokens (NanoGPT)
- Cheapest output: $1.9 per 1M tokens (NanoGPT)
- First-party: not listed separately
- Free offers: Alibaba Coding Plan, Alibaba Coding Plan (China), Alibaba Token Plan, Alibaba Token Plan (China), SCNet Token Plan, Tencent Coding Plan (China)
- Subscription plans (not per-token): Alibaba Coding Plan, Alibaba Coding Plan (China), Alibaba Token Plan, Alibaba Token Plan (China), SCNet Token Plan, Tencent Coding Plan (China)
- Released: 2026-01
- Inputs: image, text, video

## FAQ

### What is the cheapest Kimi K2.5 API?

As of Oct 4, 2026, NanoGPT has the lowest Kimi K2.5 output price at $1.9 per 1M tokens, and NanoGPT has the lowest input price at $0.3 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Kimi K2.5?

44 providers list Kimi K2.5 on Sovyron; 39 of them sell it at a metered per-token price.

### Is Kimi K2.5 free?

No provider in the Sovyron catalog lists a free tier for Kimi K2.5.

### Is Kimi K2.5 included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of Kimi K2.5?

Kimi K2.5 supports a 262k-token context window and up to 262k output tokens.

HTML page: https://sovyron.com/models/kimi-k2-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Fable 5 API prices

Claude Fable 5 (claude-fable) — 1.0M context, 128k max output.
41 metered per-token offers from 39 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Xpersona | $3 | $18.5 | $0.3 | 1.0M |
| 302.AI | $10 | $50 | — | 1.0M |
| Abacus | $10 | $50 | — | 1.0M |
| Amazon Bedrock | $10 | $50 | $1 | 1.0M |
| Amazon Bedrock (global) | $10 | $50 | $1 | 1.0M |
| Anthropic | $10 | $50 | $1 | 1.0M |
| Azure | $10 | $50 | $1 | 1.0M |
| Azure Cognitive Services | $10 | $50 | $1 | 1.0M |
| Cloudflare AI Gateway | $10 | $50 | $1 | 1.0M |
| CrossModel | $10 | $50 | $1 | 1.0M |
| DigitalOcean | $10 | $50 | $1 | 1.0M |
| Eden AI | $10 | $50 | $1 | 1.0M |
| FreeModel | $10 | $50 | $1 | 1.0M |
| Vertex | $10 | $50 | $1 | 1.0M |
| Vertex (Anthropic) | $10 | $50 | $1 | 1.0M |
| Impossibl | $10 | $50 | $1 | 1.0M |
| Kilo Gateway | $10 | $50 | $1 | 1.0M |
| DevPass (LLM Gateway) | $10 | $50 | $1 | 1.0M |
| LLM Gateway | $10 | $50 | $1 | 1.0M |
| LLM Gateway | $10 | $50 | $1 | 1.0M |
| LLM Gateway | $10 | $50 | $1 | 1.0M |
| Merge Gateway | $10 | $50 | $1 | 1.0M |
| Modelis | $10 | $50 | — | 1.0M |
| NanoGPT | $10 | $50 | $1 | 1.0M |
| Neon | $10 | $50 | $1 | 1.0M |
| Ofox | $10 | $50 | $1 | 1.0M |
| OpenCode Zen | $10 | $50 | $1 | 1.0M |
| OpenRouter | $10 | $50 | $1 | 1.0M |
| Opper | $10 | $50 | $1 | 1.0M |
| OrcaRouter | $10 | $50 | $1 | 1.0M |
| Requesty | $10 | $50 | $1 | 1.0M |
| Tempr Gateway | $10 | $50 | $1 | 1.0M |
| Vercel AI Gateway | $10 | $50 | $1 | 1.0M |
| Vivgrid | $10 | $50 | $1.25 | 1.0M |
| ZenMux | $10 | $50 | $1 | 1.0M |
| AIHubMix | $11 | $55 | $1.1 | 1.0M |
| Amazon Bedrock (eu) | $11 | $55 | $1.1 | 1.0M |
| Amazon Bedrock (us) | $11 | $55 | $1.1 | 1.0M |
| Pioneer | $11 | $55 | $1.1 | 1.0M |
| Requesty (eu) | $11 | $55 | $1.1 | 1.0M |
| Venice AI | $12 | $60 | $1.2 | 1.0M |

## Summary

- Cheapest input: $3 per 1M tokens (Xpersona)
- Cheapest output: $18.5 per 1M tokens (Xpersona)
- First-party: $50 per 1M output tokens (Anthropic)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-06-09
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Fable 5 API?

As of Oct 4, 2026, Xpersona has the lowest Claude Fable 5 output price at $18.5 per 1M tokens, and Xpersona has the lowest input price at $3 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Claude Fable 5 cost on Anthropic?

Anthropic charges $10 per 1M input tokens and $50 per 1M output tokens for Claude Fable 5.

### How many providers offer Claude Fable 5?

39 providers list Claude Fable 5 on Sovyron; 41 of them sell it at a metered per-token price.

### Is Claude Fable 5 free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is Claude Fable 5 included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Claude Fable 5?

Claude Fable 5 supports a 1.0M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/claude-fable-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.4 mini API prices

GPT-5.4 mini (gpt-mini) — 400k context, 128k max output.
36 metered per-token offers from 38 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Xpersona | $0.375 | $4 | $0.0375 | 272k |
| Ofox | $0.6 | $3.6 | $0.06 | 400k |
| Poe | $0.68 | $4 | $0.068 | 400k |
| 302.AI | $0.75 | $4.5 | — | 400k |
| Abacus | $0.75 | $4.5 | $0.075 | 400k |
| AIHubMix | $0.75 | $4.5 | $0.075 | 400k |
| Azure | $0.75 | $4.5 | $0.075 | 400k |
| Azure Cognitive Services | $0.75 | $4.5 | $0.075 | 400k |
| Cloudflare AI Gateway | $0.75 | $4.5 | $0.075 | 128k |
| CrossModel | $0.75 | $4.5 | $0.075 | 400k |
| Databricks | $0.75 | $4.5 | $0.075 | 400k |
| DigitalOcean | $0.75 | $4.5 | $0.075 | 400k |
| Eden AI | $0.75 | $4.5 | $0.075 | 400k |
| FastRouter | $0.75 | $4.5 | — | 400k |
| FreeModel | $0.75 | $4.5 | $0.075 | 400k |
| FrogBot | $0.75 | $4.5 | $0.075 | 400k |
| Impossibl | $0.75 | $4.5 | $0.075 | 400k |
| Kilo Gateway | $0.75 | $4.5 | $0.075 | 400k |
| DevPass (LLM Gateway) | $0.75 | $4.5 | $0.075 | 400k |
| LLM Gateway | $0.75 | $4.5 | $0.075 | 400k |
| LLM Gateway | $0.75 | $4.5 | $0.075 | 400k |
| Merge Gateway | $0.75 | $4.5 | $0.075 | 400k |
| NanoGPT | $0.75 | $4.5 | $0.075 | 400k |
| NEAR AI Cloud | $0.75 | $4.5 | $0.075 | 400k |
| Neon | $0.75 | $4.5 | $0.075 | 400k |
| OpenAI | $0.75 | $4.5 | $0.075 | 400k |
| OpenCode Zen | $0.75 | $4.5 | $0.075 | 400k |
| OpenRouter | $0.75 | $4.5 | $0.075 | 400k |
| Opper | $0.75 | $4.5 | $0.075 | 400k |
| OrcaRouter | $0.75 | $4.5 | $0.075 | 400k |
| Pioneer | $0.75 | $4.5 | $0.075 | 400k |
| Requesty | $0.75 | $4.5 | $0.075 | 400k |
| Vercel AI Gateway | $0.75 | $4.5 | $0.075 | 400k |
| Vivgrid | $0.75 | $4.5 | $0.075 | 400k |
| ZenMux | $0.75 | $4.5 | — | 400k |
| Venice AI | $0.9375 | $5.625 | $0.0938 | 400k |

## Summary

- Cheapest input: $0.375 per 1M tokens (Xpersona)
- Cheapest output: $3.6 per 1M tokens (Ofox)
- First-party: $4.5 per 1M output tokens (OpenAI)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-03-17
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.4 mini API?

As of Oct 4, 2026, Ofox has the lowest GPT-5.4 mini output price at $3.6 per 1M tokens, and Xpersona has the lowest input price at $0.375 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5.4 mini cost on OpenAI?

OpenAI charges $0.75 per 1M input tokens and $4.5 per 1M output tokens for GPT-5.4 mini.

### How many providers offer GPT-5.4 mini?

38 providers list GPT-5.4 mini on Sovyron; 36 of them sell it at a metered per-token price.

### Is GPT-5.4 mini free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is GPT-5.4 mini included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of GPT-5.4 mini?

GPT-5.4 mini supports a 400k-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-4-mini/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.6 Sol API prices

GPT-5.6 Sol (gpt-sol) — 1.1M context, 128k max output.
40 metered per-token offers from 39 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Cloudflare AI Gateway | $2 | $10 | $0.25 | 1.1M |
| NanoGPT | $2 | $10 | $0.2 | 1.1M |
| OpenRouter | $2 | $10 | $0.2 | 1.1M |
| Xpersona | $1.5 | $12 | $0.15 | 372k |
| Ofox | $2.5 | $15 | $0.25 | 1.1M |
| routing.run | $2.5 | $15 | — | 1.0M |
| Amazon Bedrock (global) | $4 | $20 | $0.4 | 1.1M |
| Azure | $4 | $20 | $0.5 | 1.1M |
| CrossModel | $4 | $20 | $0.4 | 1.1M |
| DigitalOcean | $4 | $20 | $0.4 | 1.1M |
| Eden AI | $4 | $20 | $0.4 | 1.1M |
| Kilo Gateway | $4 | $20 | $0.4 | 1.1M |
| Kilo Gateway | $4 | $20 | $0.4 | 1.1M |
| DevPass (LLM Gateway) | $4 | $20 | $0.4 | 1.1M |
| LLM Gateway | $4 | $20 | $0.4 | 1.1M |
| LLM Gateway | $4 | $20 | $0.4 | 1.1M |
| OpenAI | $4 | $20 | $0.4 | 1.1M |
| OpenCode Zen | $4 | $20 | $0.4 | 1.1M |
| OrcaRouter | $4 | $20 | $0.4 | 1.1M |
| Requesty | $4 | $20 | $0.4 | 1.1M |
| Vercel AI Gateway | $4 | $20 | $0.4 | 1.1M |
| Cortecs | $4.399 | $21.998 | $0.44 | 1.1M |
| Amazon Bedrock | $4.4 | $22 | $0.44 | 1.1M |
| Amazon Bedrock (us) | $4.4 | $22 | $0.44 | 1.1M |
| Requesty (eu) | $4.4 | $22 | $0.44 | 1.1M |
| Venice AI | $5 | $25 | $0.5 | 1.0M |
| 302.AI | $5 | $30 | — | 1.1M |
| Abacus | $5 | $30 | $0.5 | 1.0M |
| AI-ROUTER | $5 | $30 | $0.5 | 1.1M |
| AIHubMix | $5 | $30 | $0.5 | 1.1M |
| Azure Cognitive Services | $5 | $30 | $0.5 | 1.1M |
| Databricks | $5 | $30 | $0.5 | 1.1M |
| Impossibl | $5 | $30 | $0.5 | 1.1M |
| Merge Gateway | $5 | $30 | $0.5 | 1.1M |
| Neon | $5 | $30 | $0.5 | 1.1M |
| Opper | $5 | $30 | $0.5 | 1.0M |
| Pioneer | $5 | $30 | $0.5 | 1.1M |
| SAP AI Core | $5 | $30 | $0.5 | 1.1M |
| Vivgrid | $5 | $30 | $0.5 | 1.1M |
| ZenMux | $5 | $30 | $0.5 | 1.1M |

## Summary

- Cheapest input: $1.5 per 1M tokens (Xpersona)
- Cheapest output: $10 per 1M tokens (Cloudflare AI Gateway)
- First-party: $20 per 1M output tokens (OpenAI)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-07-09
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.6 Sol API?

As of Oct 4, 2026, Cloudflare AI Gateway has the lowest GPT-5.6 Sol output price at $10 per 1M tokens, and Xpersona has the lowest input price at $1.5 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5.6 Sol cost on OpenAI?

OpenAI charges $4 per 1M input tokens and $20 per 1M output tokens for GPT-5.6 Sol.

### How many providers offer GPT-5.6 Sol?

39 providers list GPT-5.6 Sol on Sovyron; 40 of them sell it at a metered per-token price.

### Is GPT-5.6 Sol free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is GPT-5.6 Sol included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of GPT-5.6 Sol?

GPT-5.6 Sol supports a 1.1M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-6-sol/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.6 Terra API prices

GPT-5.6 Terra (gpt-terra) — 1.1M context, 128k max output.
41 metered per-token offers from 38 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Xpersona | $1.5 | $2 | $0.15 | 372k |
| routing.run | $1.5 | $9 | — | 1.0M |
| 302.AI | $2 | $12 | — | 1.1M |
| Amazon Bedrock (global) | $2 | $12 | $0.2 | 1.1M |
| Azure | $2 | $12 | $0.2 | 1.1M |
| Cloudflare AI Gateway | $2 | $12 | $0.2 | 1.1M |
| CrossModel | $2 | $12 | $0.2 | 1.1M |
| DigitalOcean | $2 | $12 | $0.2 | 1.1M |
| Eden AI | $2 | $12 | $0.2 | 1.1M |
| Impossibl | $2 | $12 | $0.2 | 1.1M |
| Kilo Gateway | $2 | $12 | $0.2 | 1.1M |
| Kilo Gateway | $2 | $12 | $0.2 | 1.1M |
| DevPass (LLM Gateway) | $2 | $12 | $0.2 | 1.1M |
| LLM Gateway | $2 | $12 | $0.2 | 1.1M |
| LLM Gateway | $2 | $12 | $0.2 | 1.1M |
| Merge Gateway | $2 | $12 | $0.2 | 1.1M |
| NanoGPT | $2 | $12 | $0.2 | 1.1M |
| Neon | $2 | $12 | $0.2 | 1.1M |
| Ofox | $2 | $12 | $0.2 | 1.1M |
| OpenAI | $2 | $12 | $0.2 | 1.1M |
| OpenRouter | $2 | $12 | $0.2 | 1.1M |
| Opper | $2 | $12 | $0.2 | 1.0M |
| OrcaRouter | $2 | $12 | $0.2 | 1.1M |
| Requesty | $2 | $12 | $0.2 | 1.1M |
| Vercel AI Gateway | $2 | $12 | $0.2 | 1.1M |
| Cortecs | $2.2 | $13.199 | $0.219 | 1.1M |
| Amazon Bedrock (india) | $2.2 | $13.2 | $0.22 | 1.1M |
| Amazon Bedrock | $2.2 | $13.2 | $0.22 | 1.1M |
| Amazon Bedrock (us) | $2.2 | $13.2 | $0.22 | 1.1M |
| Requesty (eu) | $2.2 | $13.2 | $0.22 | 1.1M |
| Abacus | $2.5 | $15 | $0.25 | 1.0M |
| AI-ROUTER | $2.5 | $15 | $0.25 | 1.1M |
| AIHubMix | $2.5 | $15 | $0.25 | 1.1M |
| Azure Cognitive Services | $2.5 | $15 | $0.25 | 1.1M |
| Databricks | $2.5 | $15 | $0.25 | 1.1M |
| OpenCode Zen | $2.5 | $15 | $0.25 | 1.1M |
| Pioneer | $2.5 | $15 | $0.25 | 1.1M |
| SAP AI Core | $2.5 | $15 | $0.25 | 1.1M |
| Venice AI | $2.5 | $15 | $0.25 | 1.0M |
| Vivgrid | $2.5 | $15 | $0.25 | 1.1M |
| ZenMux | $2.5 | $15 | $0.25 | 1.1M |

## Summary

- Cheapest input: $1.5 per 1M tokens (Xpersona)
- Cheapest output: $2 per 1M tokens (Xpersona)
- First-party: $12 per 1M output tokens (OpenAI)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-07-09
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.6 Terra API?

As of Oct 4, 2026, Xpersona has the lowest GPT-5.6 Terra output price at $2 per 1M tokens, and Xpersona has the lowest input price at $1.5 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5.6 Terra cost on OpenAI?

OpenAI charges $2 per 1M input tokens and $12 per 1M output tokens for GPT-5.6 Terra.

### How many providers offer GPT-5.6 Terra?

38 providers list GPT-5.6 Terra on Sovyron; 41 of them sell it at a metered per-token price.

### Is GPT-5.6 Terra free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is GPT-5.6 Terra included in a subscription plan?

Yes. 4 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of GPT-5.6 Terra?

GPT-5.6 Terra supports a 1.1M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-6-terra/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Sonnet 5 API prices

Claude Sonnet 5 (claude-sonnet) — 1.0M context, 1.0M max output.
44 metered per-token offers from 38 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| UnoRouter | $1.44 | $7.2 | — | 1.0M |
| 302.AI | $2 | $10 | — | 1.0M |
| AIHubMix | $2 | $10 | $0.2 | 1.0M |
| Amazon Bedrock | $2 | $10 | $0.2 | 1.0M |
| Amazon Bedrock (global) | $2 | $10 | $0.2 | 1.0M |
| Anthropic | $2 | $10 | $0.2 | 1.0M |
| Azure | $2 | $10 | $0.2 | 1.0M |
| Azure Cognitive Services | $2 | $10 | $0.2 | 1.0M |
| Cloudflare AI Gateway | $2 | $10 | $0.2 | 1.0M |
| CrossModel | $2 | $10 | $0.2 | 1.0M |
| DigitalOcean | $2 | $10 | $0.2 | 1.0M |
| Eden AI | $2 | $10 | $0.2 | 1.0M |
| Vertex | $2 | $10 | $0.2 | 1.0M |
| Vertex (Anthropic) | $2 | $10 | $0.2 | 1.0M |
| Impossibl | $2 | $10 | $0.2 | 1.0M |
| Kilo Gateway | $2 | $10 | $0.2 | 1.0M |
| DevPass (LLM Gateway) | $2 | $10 | $0.2 | 1.0M |
| LLM Gateway | $2 | $10 | $0.2 | 1.0M |
| LLM Gateway | $2 | $10 | $0.2 | 1.0M |
| LLM Gateway | $2 | $10 | $0.2 | 1.0M |
| LLM Gateway | $2 | $10 | $0.2 | 1.0M |
| Merge Gateway | $2 | $10 | $0.2 | 1.0M |
| NanoGPT | $2 | $10 | $0.2 | 1.0M |
| Neon | $2 | $10 | $0.2 | 1.0M |
| Ofox | $2 | $10 | $0.2 | 1.0M |
| OpenCode Zen | $2 | $10 | $0.2 | 1.0M |
| OpenRouter | $2 | $10 | $0.2 | 1.0M |
| OrcaRouter | $2 | $10 | $0.2 | 1.0M |
| Pioneer | $2 | $10 | $0.2 | 1.0M |
| Requesty | $2 | $10 | $0.2 | 1.0M |
| Tempr Gateway | $2 | $10 | $0.2 | 1.0M |
| Vercel AI Gateway | $2 | $10 | $0.2 | 1.0M |
| Vivgrid | $2 | $10 | $0.2 | 1.0M |
| ZenMux | $2 | $10 | $0.2 | 1.0M |
| Amazon Bedrock (au) | $2.2 | $11 | $0.22 | 1.0M |
| Amazon Bedrock (eu) | $2.2 | $11 | $0.22 | 1.0M |
| Amazon Bedrock (india) | $2.2 | $11 | $0.22 | 1.0M |
| Amazon Bedrock (jp) | $2.2 | $11 | $0.22 | 1.0M |
| Amazon Bedrock (us) | $2.2 | $11 | $0.22 | 1.0M |
| Cortecs | $2.2 | $11 | $0.219 | 1.0M |
| Opper | $2.2 | $11 | $0.22 | 1.0M |
| Requesty (eu) | $2.2 | $11 | $0.22 | 1.0M |
| Venice AI | $2.5 | $12.5 | $0.25 | 1.0M |
| Abacus | $3 | $15 | — | 1.0M |

## Summary

- Cheapest input: $1.44 per 1M tokens (UnoRouter)
- Cheapest output: $7.2 per 1M tokens (UnoRouter)
- First-party: $10 per 1M output tokens (Anthropic)
- Free offers: Kenari, ZenMux
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-06-30
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Sonnet 5 API?

As of Oct 4, 2026, UnoRouter has the lowest Claude Sonnet 5 output price at $7.2 per 1M tokens, and UnoRouter has the lowest input price at $1.44 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Claude Sonnet 5 cost on Anthropic?

Anthropic charges $2 per 1M input tokens and $10 per 1M output tokens for Claude Sonnet 5.

### How many providers offer Claude Sonnet 5?

38 providers list Claude Sonnet 5 on Sovyron; 44 of them sell it at a metered per-token price.

### Is Claude Sonnet 5 free?

2 provider(s) list a free-tier offer: Kenari, ZenMux. Free tiers usually have rate limits.

### Is Claude Sonnet 5 included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Claude Sonnet 5?

Claude Sonnet 5 supports a 1.0M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/claude-sonnet-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT OSS 20B API prices

GPT OSS 20B (gpt-oss) — 131k context, 131k max output.
40 metered per-token offers from 39 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Kilo Gateway | $0.018 | $0.09 | $0.009 | 131k |
| OpenRouter | $0.018 | $0.09 | $0.009 | 131k |
| CoreWeave | $0.03 | $0.13 | $0.03 | 131k |
| Deep Infra | $0.03 | $0.14 | — | 131k |
| Eden AI | $0.03 | $0.14 | — | 131k |
| IO.NET | $0.03 | $0.14 | $0.015 | 64k |
| Vercel AI Gateway | $0.03 | $0.14 | — | 131k |
| Merge Gateway | $0.04 | $0.15 | $0.02 | 128k |
| NovitaAI | $0.04 | $0.15 | — | 131k |
| SiliconFlow | $0.04 | $0.18 | — | 131k |
| Cortecs | $0.045 | $0.167 | — | 131k |
| DevPass (LLM Gateway) | $0.04 | $0.19 | $0.01 | 131k |
| Clarifai | $0.045 | $0.18 | — | 131k |
| Eden AI | $0.05 | $0.18 | — | 131k |
| OVHcloud AI Endpoints | $0.05 | $0.18 | — | 131k |
| Helicone | $0.05 | $0.2 | — | 131k |
| Databricks | $0.05 | $0.2 | — | 131k |
| FastRouter | $0.05 | $0.2 | — | 131k |
| FrogBot | $0.07 | $0.2 | — | 131k |
| Amazon Bedrock | $0.07 | $0.3 | — | 131k |
| Amazon Bedrock | $0.07 | $0.3 | — | 131k |
| Impossibl | $0.07 | $0.3 | $0.035 | 131k |
| Neon | $0.07 | $0.3 | — | 131k |
| OCI Generative AI | $0.07 | $0.3 | — | 128k |
| Ollama Cloud | $0.07 | $0.3 | $0.035 | 131k |
| Pioneer | $0.07 | $0.3 | $0.035 | 131k |
| Eden AI | $0.07 | $0.3 | $0.007 | 131k |
| Eden AI | $0.075 | $0.3 | $0.0375 | 131k |
| Groq | $0.075 | $0.3 | $0.0375 | 131k |
| Impossibl | $0.075 | $0.3 | $0.0375 | 131k |
| Tempr Gateway | $0.075 | $0.3 | $0.0375 | 131k |
| DigitalOcean | $0.05 | $0.45 | $0.01 | 128k |
| Hugging Face | $0.1 | $0.5 | — | 131k |
| LLM Gateway | $0.1 | $0.5 | — | 131k |
| STACKIT | $0.18 | $0.29 | — | 131k |
| Opper | $0.1162 | $0.4881 | — | 128k |
| Cloudflare Workers AI | $0.2 | $0.3 | — | 128k |
| Eden AI | $0.2 | $0.3 | — | 128k |
| NanoGPT | $0.2 | $0.3 | — | 128k |
| Regolo AI | $0.4 | $1.8 | — | 128k |

## Summary

- Cheapest input: $0.018 per 1M tokens (Kilo Gateway)
- Cheapest output: $0.09 per 1M tokens (Kilo Gateway)
- First-party: not listed separately
- Free offers: Kenari, LMStudio, Nvidia, QVAC
- Subscription plans (not per-token): none
- Released: 2025-08-05
- Inputs: image, text

## FAQ

### What is the cheapest GPT OSS 20B API?

As of Oct 4, 2026, Kilo Gateway has the lowest GPT OSS 20B output price at $0.09 per 1M tokens, and Kilo Gateway has the lowest input price at $0.018 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer GPT OSS 20B?

39 providers list GPT OSS 20B on Sovyron; 40 of them sell it at a metered per-token price.

### Is GPT OSS 20B free?

4 provider(s) list a free-tier offer: Kenari, LMStudio, Nvidia, QVAC. Free tiers usually have rate limits.

### What is the context window of GPT OSS 20B?

GPT OSS 20B supports a 131k-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/gpt-oss-20b/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5 Mini API prices

GPT-5 Mini (gpt-mini) — 400k context, 128k max output.
33 metered per-token offers from 35 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| QiHang | $0.04 | $0.29 | — | 200k |
| Ofox | $0.2 | $1.6 | $0.024 | 256k |
| Poe | $0.22 | $1.8 | $0.022 | 400k |
| Jiekou.AI | $0.225 | $1.8 | — | 400k |
| 302.AI | $0.25 | $2 | — | 400k |
| Abacus | $0.25 | $2 | $0.025 | 400k |
| Azure | $0.25 | $2 | $0.03 | 400k |
| Azure Cognitive Services | $0.25 | $2 | $0.03 | 400k |
| Cloudflare AI Gateway | $0.25 | $2 | $0.025 | 128k |
| Databricks | $0.25 | $2 | $0.025 | 400k |
| DigitalOcean | $0.25 | $2 | $0.025 | 400k |
| Eden AI | $0.25 | $2 | $0.025 | 400k |
| FastRouter | $0.25 | $2 | $0.025 | 400k |
| Helicone | $0.25 | $2 | $0.025 | 400k |
| Impossibl | $0.25 | $2 | $0.025 | 400k |
| Kilo Gateway | $0.25 | $2 | $0.025 | 400k |
| DevPass (LLM Gateway) | $0.25 | $2 | $0.025 | 400k |
| LLM Gateway | $0.25 | $2 | $0.025 | 400k |
| LLM Gateway | $0.25 | $2 | $0.025 | 400k |
| Merge Gateway | $0.25 | $2 | $0.025 | 400k |
| NanoGPT | $0.25 | $2 | $0.025 | 400k |
| NEAR AI Cloud | $0.25 | $2 | $0.025 | 400k |
| Neon | $0.25 | $2 | $0.025 | 400k |
| OpenAI | $0.25 | $2 | $0.025 | 400k |
| OpenRouter | $0.25 | $2 | $0.025 | 400k |
| OrcaRouter | $0.25 | $2 | $0.025 | 400k |
| Perplexity Agent | $0.25 | $2 | $0.025 | 400k |
| Pioneer | $0.25 | $2 | $0.025 | 400k |
| SAP AI Core | $0.25 | $2 | $0.025 | 400k |
| Vercel AI Gateway | $0.25 | $2 | $0.025 | 400k |
| Vivgrid | $0.25 | $2 | $0.03 | 272k |
| Requesty (eu) | $0.275 | $2.2 | $0.0275 | 200k |
| Cortecs | $0.279 | $2.192 | $0.056 | 400k |

## Summary

- Cheapest input: $0.04 per 1M tokens (QiHang)
- Cheapest output: $0.29 per 1M tokens (QiHang)
- First-party: $2 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): GitHub Copilot
- Released: 2025-08-07
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5 Mini API?

As of Oct 4, 2026, QiHang has the lowest GPT-5 Mini output price at $0.29 per 1M tokens, and QiHang has the lowest input price at $0.04 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5 Mini cost on OpenAI?

OpenAI charges $0.25 per 1M input tokens and $2 per 1M output tokens for GPT-5 Mini.

### How many providers offer GPT-5 Mini?

35 providers list GPT-5 Mini on Sovyron; 33 of them sell it at a metered per-token price.

### Is GPT-5 Mini free?

No provider in the Sovyron catalog lists a free tier for GPT-5 Mini.

### Is GPT-5 Mini included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of GPT-5 Mini?

GPT-5 Mini supports a 400k-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-mini/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.4 nano API prices

GPT-5.4 nano (gpt-nano) — 1.0M context, 128k max output.
33 metered per-token offers from 34 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $0.16 | $1 | $0.016 | 400k |
| Poe | $0.18 | $1.1 | $0.018 | 400k |
| 302.AI | $0.2 | $1.25 | — | 400k |
| Abacus | $0.2 | $1.25 | $0.02 | 400k |
| AIHubMix | $0.2 | $1.25 | $0.02 | 400k |
| Azure | $0.2 | $1.25 | $0.02 | 400k |
| Azure Cognitive Services | $0.2 | $1.25 | $0.02 | 400k |
| Cloudflare AI Gateway | $0.2 | $1.25 | $0.02 | 128k |
| CrossModel | $0.2 | $1.25 | $0.02 | 400k |
| Databricks | $0.2 | $1.25 | $0.02 | 400k |
| DigitalOcean | $0.2 | $1.25 | $0.02 | 400k |
| Eden AI | $0.2 | $1.25 | $0.02 | 400k |
| FastRouter | $0.2 | $1.25 | — | 400k |
| FrogBot | $0.2 | $1.25 | $0.02 | 400k |
| Impossibl | $0.2 | $1.25 | $0.02 | 400k |
| Kilo Gateway | $0.2 | $1.25 | $0.02 | 400k |
| DevPass (LLM Gateway) | $0.2 | $1.25 | $0.02 | 400k |
| LLM Gateway | $0.2 | $1.25 | $0.02 | 400k |
| LLM Gateway | $0.2 | $1.25 | $0.02 | 400k |
| Merge Gateway | $0.2 | $1.25 | $0.02 | 400k |
| NanoGPT | $0.2 | $1.25 | $0.02 | 400k |
| NEAR AI Cloud | $0.2 | $1.25 | $0.02 | 400k |
| Neon | $0.2 | $1.25 | $0.02 | 400k |
| OpenAI | $0.2 | $1.25 | $0.02 | 400k |
| OpenCode Zen | $0.2 | $1.25 | $0.02 | 400k |
| OpenRouter | $0.2 | $1.25 | $0.02 | 400k |
| Opper | $0.2 | $1.25 | $0.02 | 400k |
| OrcaRouter | $0.2 | $1.25 | $0.02 | 400k |
| Pioneer | $0.2 | $1.25 | $0.02 | 1.0M |
| Requesty | $0.2 | $1.25 | $0.02 | 400k |
| Vercel AI Gateway | $0.2 | $1.25 | $0.02 | 400k |
| Vivgrid | $0.2 | $1.25 | $0.02 | 400k |
| ZenMux | $0.2 | $1.25 | — | 400k |

## Summary

- Cheapest input: $0.16 per 1M tokens (Ofox)
- Cheapest output: $1 per 1M tokens (Ofox)
- First-party: $1.25 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-03-17
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.4 nano API?

As of Oct 4, 2026, Ofox has the lowest GPT-5.4 nano output price at $1 per 1M tokens, and Ofox has the lowest input price at $0.16 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5.4 nano cost on OpenAI?

OpenAI charges $0.2 per 1M input tokens and $1.25 per 1M output tokens for GPT-5.4 nano.

### How many providers offer GPT-5.4 nano?

34 providers list GPT-5.4 nano on Sovyron; 33 of them sell it at a metered per-token price.

### Is GPT-5.4 nano free?

No provider in the Sovyron catalog lists a free tier for GPT-5.4 nano.

### Is GPT-5.4 nano included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of GPT-5.4 nano?

GPT-5.4 nano supports a 1.0M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-4-nano/
Full dataset: https://sovyron.com/data/catalog.json

---

# Gemini 3.5 Flash API prices

Gemini 3.5 Flash (gemini-flash) — 1.0M context, 128k max output.
35 metered per-token offers from 34 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| UnoRouter | $0.1857 | $1.1142 | — | 1.0M |
| Kilo Gateway | $0.75 | $4.5 | $0.075 | 1.0M |
| 302.AI | $1.5 | $9 | — | 1.0M |
| Abacus | $1.5 | $9 | $0.15 | 1.0M |
| AIHubMix | $1.5 | $9 | $1.5 | 1.0M |
| CrossModel | $1.5 | $9 | $0.15 | 1.0M |
| Eden AI | $1.5 | $9 | $0.15 | 1.0M |
| Eden AI | $1.5 | $9 | $0.15 | 1.0M |
| FastRouter | $1.5 | $9 | — | 1.0M |
| Google | $1.5 | $9 | $0.15 | 1.0M |
| Vertex | $1.5 | $9 | $0.15 | 1.0M |
| Impossibl | $1.5 | $9 | $0.15 | 1.0M |
| DevPass (LLM Gateway) | $1.5 | $9 | $0.15 | 1.0M |
| LLM Gateway | $1.5 | $9 | $0.15 | 1.0M |
| LLM Gateway | $1.5 | $9 | $0.15 | 1.0M |
| Merge Gateway | $1.5 | $9 | $0.15 | 1.0M |
| NanoGPT | $1.5 | $9 | $0.15 | 1.0M |
| NEAR AI Cloud | $1.5 | $9 | $0.15 | 1.0M |
| Neon | $1.5 | $9 | $0.15 | 1.0M |
| Ofox | $1.5 | $9 | $0.15 | 1.0M |
| OpenCode Zen | $1.5 | $9 | $0.15 | 1.0M |
| OpenRouter | $1.5 | $9 | $0.15 | 1.0M |
| Opper | $1.5 | $9 | $0.15 | 1.0M |
| OrcaRouter | $1.5 | $9 | $0.15 | 1.0M |
| Pioneer | $1.5 | $9 | $0.15 | 1.0M |
| Requesty | $1.5 | $9 | $0.15 | 1.0M |
| SAP AI Core | $1.5 | $9 | $0.15 | 1.0M |
| Tempr Gateway | $1.5 | $9 | $0.15 | 1.0M |
| Vercel AI Gateway | $1.5 | $9 | $0.15 | 1.0M |
| ZenMux | $1.5 | $9 | $0.15 | 1.0M |
| Poe | $1.5152 | $9.0909 | $0.1515 | 1.0M |
| Venice AI | $1.55 | $9.45 | $0.155 | 1.0M |
| Cortecs | $1.649 | $9.899 | $0.165 | 1.0M |
| Requesty (eu) | $1.65 | $9.9 | $0.165 | 1.0M |
| Xpersona | $1.55 | $12.2 | $0.155 | 1.0M |

## Summary

- Cheapest input: $0.1857 per 1M tokens (UnoRouter)
- Cheapest output: $1.1142 per 1M tokens (UnoRouter)
- First-party: $9 per 1M output tokens (Google)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-05-19
- Inputs: audio, image, pdf, text, video

## FAQ

### What is the cheapest Gemini 3.5 Flash API?

As of Oct 4, 2026, UnoRouter has the lowest Gemini 3.5 Flash output price at $1.1142 per 1M tokens, and UnoRouter has the lowest input price at $0.1857 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Gemini 3.5 Flash cost on Google?

Google charges $1.5 per 1M input tokens and $9 per 1M output tokens for Gemini 3.5 Flash.

### How many providers offer Gemini 3.5 Flash?

34 providers list Gemini 3.5 Flash on Sovyron; 35 of them sell it at a metered per-token price.

### Is Gemini 3.5 Flash free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is Gemini 3.5 Flash included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Gemini 3.5 Flash?

Gemini 3.5 Flash supports a 1.0M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gemini-3-5-flash/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Opus 5 API prices

Claude Opus 5 (claude-opus) — 1.0M context, 128k max output.
41 metered per-token offers from 35 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| 302.AI | $5 | $25 | — | 1.0M |
| Abacus | $5 | $25 | — | 1.0M |
| AIHubMix | $5 | $25 | $0.5 | 1.0M |
| Amazon Bedrock | $5 | $25 | $0.5 | 1.0M |
| Amazon Bedrock (global) | $5 | $25 | $0.5 | 1.0M |
| Anthropic | $5 | $25 | $0.5 | 1.0M |
| Azure | $5 | $25 | $0.5 | 1.0M |
| Azure Cognitive Services | $5 | $25 | $0.5 | 1.0M |
| Cloudflare AI Gateway | $5 | $25 | $0.5 | 1.0M |
| CrossModel | $5 | $25 | $0.5 | 1.0M |
| DigitalOcean | $5 | $25 | $0.5 | 1.0M |
| Eden AI | $5 | $25 | $0.5 | 1.0M |
| Vertex | $5 | $25 | $0.5 | 1.0M |
| Vertex (Anthropic) | $5 | $25 | $0.5 | 1.0M |
| Kilo Gateway | $5 | $25 | $0.5 | 1.0M |
| DevPass (LLM Gateway) | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| LLM Gateway | $5 | $25 | $0.5 | 1.0M |
| Merge Gateway | $5 | $25 | $0.5 | 1.0M |
| NanoGPT | $5 | $25 | $0.5 | 1.0M |
| Neon | $5 | $25 | $0.5 | 1.0M |
| Ofox | $5 | $25 | $0.5 | 1.0M |
| OpenCode Zen | $5 | $25 | $0.5 | 1.0M |
| OpenRouter | $5 | $25 | $0.5 | 1.0M |
| OrcaRouter | $5 | $25 | $0.5 | 1.0M |
| Pioneer | $5 | $25 | $0.5 | 1.0M |
| Requesty | $5 | $25 | $0.5 | 1.0M |
| Tempr Gateway | $5 | $25 | $0.5 | 1.0M |
| Vercel AI Gateway | $5 | $25 | $0.5 | 1.0M |
| Vivgrid | $5 | $25 | $0.5 | 1.0M |
| Cortecs | $5.5 | $27.498 | $0.55 | 1.0M |
| Amazon Bedrock (au) | $5.5 | $27.5 | $0.55 | 1.0M |
| Amazon Bedrock (eu) | $5.5 | $27.5 | $0.55 | 1.0M |
| Amazon Bedrock (india) | $5.5 | $27.5 | $0.55 | 1.0M |
| Amazon Bedrock (jp) | $5.5 | $27.5 | $0.55 | 1.0M |
| Amazon Bedrock (us) | $5.5 | $27.5 | $0.55 | 1.0M |
| Opper | $5.5 | $27.5 | $0.55 | 1.0M |
| Requesty (eu) | $5.5 | $27.5 | $0.55 | 1.0M |
| Venice AI | $6 | $30 | $0.6 | 1.0M |
| Pioneer | $10 | $50 | $1 | 1.0M |

## Summary

- Cheapest input: $5 per 1M tokens (302.AI)
- Cheapest output: $25 per 1M tokens (302.AI)
- First-party: $25 per 1M output tokens (Anthropic)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-07-24
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Opus 5 API?

As of Oct 4, 2026, 302.AI has the lowest Claude Opus 5 output price at $25 per 1M tokens, and 302.AI has the lowest input price at $5 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Claude Opus 5 cost on Anthropic?

Anthropic charges $5 per 1M input tokens and $25 per 1M output tokens for Claude Opus 5.

### How many providers offer Claude Opus 5?

35 providers list Claude Opus 5 on Sovyron; 41 of them sell it at a metered per-token price.

### Is Claude Opus 5 free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is Claude Opus 5 included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Claude Opus 5?

Claude Opus 5 supports a 1.0M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/claude-opus-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# DeepSeek V4 Pro 0813 API prices

DeepSeek V4 Pro 0813 (deepseek-thinking) — 1.0M context, 1.0M max output.
39 metered per-token offers from 34 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| OrcaRouter | $0.442 | $0.884 | $0.06 | 1.0M |
| RunInfra | $0.6 | $1.9 | $0.03 | 1.0M |
| Eden AI | $0.66 | $1.98 | $0.066 | 1.0M |
| Eden AI | $0.66 | $1.98 | $0.022 | 1.0M |
| Ollama Cloud | $0.66 | $1.98 | $0.022 | 1.0M |
| Vercel AI Gateway | $0.66 | $1.98 | $0.066 | 1.0M |
| AIHubMix | $0.6918 | $2.0754 | $0.0231 | 1.0M |
| Ofox | $0.924 | $2.772 | $0.0308 | 1.0M |
| NanoGPT | $1.1 | $2.5 | $0.04 | 1.0M |
| OpenRouter | $0.55 | $4.2 | $0.45 | 1.0M |
| Deep Infra | $1.3 | $2.6 | $0.1 | 1.0M |
| Eden AI | $1.3 | $2.6 | $0.1 | 1.0M |
| IteraCompute | $1.1 | $3.3 | $0.11 | 1.0M |
| Vivgrid | $1.35 | $3 | $0.05 | 1.0M |
| CoreWeave | $1.31 | $3.96 | $0.044 | 1.0M |
| Eden AI | $1.32 | $3.96 | $0.132 | 1.0M |
| Arcee | $1.32 | $3.96 | $0.044 | 1.0M |
| Baseten | $1.32 | $3.96 | — | 1.0M |
| Cloudflare Workers AI | $1.32 | $3.96 | $0.044 | 1.0M |
| DigitalOcean | $1.32 | $3.96 | $0.044 | 1.0M |
| Eden AI | $1.32 | $3.96 | $0.044 | 1.0M |
| Eden AI | $1.32 | $3.96 | $1.32 | 979k |
| Eden AI | $1.32 | $3.96 | $0.13 | 1.0M |
| EmpirioLabs AI | $1.32 | $3.96 | $1.32 | 1.0M |
| Hugging Face | $1.32 | $3.96 | — | 1.0M |
| Kilo Gateway | $1.32 | $3.96 | $0.044 | 1.0M |
| Nebius Token Factory | $1.32 | $3.96 | $1.32 | 979k |
| Requesty | $1.32 | $3.96 | $0.044 | 1.0M |
| SiliconFlow | $1.32 | $3.96 | $0.044 | 1.0M |
| Together AI | $1.32 | $3.96 | $0.13 | 1.0M |
| Volcengine Ark | $1.3359 | $4.0077 | $0.0445 | 1.0M |
| Charm Hyper | $1.4372 | $4.3116 | $0.0479 | 1.0M |
| Merge Gateway | $1.74 | $3.48 | $0.0036 | 1.0M |
| Requesty (eu) | $1.75 | $3.5 | $0.44 | 1.0M |
| Bothub | $1.61 | $4.84 | — | 1.0M |
| Venice AI | $1.65 | $4.95 | $0.165 | 1.0M |
| Cortecs | $2 | $3.999 | $0.5 | 1.0M |
| Eden AI | $2 | $4 | $0.5 | 1.0M |
| TensorX | $2 | $4 | $0.5 | 1.0M |

## Summary

- Cheapest input: $0.442 per 1M tokens (OrcaRouter)
- Cheapest output: $0.884 per 1M tokens (OrcaRouter)
- First-party: not listed separately
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China), SCNet Token Plan
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China), SCNet Token Plan
- Released: 2026-08-12
- Inputs: text

## FAQ

### What is the cheapest DeepSeek V4 Pro 0813 API?

As of Oct 4, 2026, OrcaRouter has the lowest DeepSeek V4 Pro 0813 output price at $0.884 per 1M tokens, and OrcaRouter has the lowest input price at $0.442 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer DeepSeek V4 Pro 0813?

34 providers list DeepSeek V4 Pro 0813 on Sovyron; 39 of them sell it at a metered per-token price.

### Is DeepSeek V4 Pro 0813 free?

No provider in the Sovyron catalog lists a free tier for DeepSeek V4 Pro 0813.

### Is DeepSeek V4 Pro 0813 included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 supports a 1.0M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/deepseek-v4-pro-0813/
Full dataset: https://sovyron.com/data/catalog.json

---

# Gemini 2.5 Flash API prices

Gemini 2.5 Flash (gemini-flash) — 1.1M context, 66k max output.
34 metered per-token offers from 34 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| QiHang | $0.09 | $0.71 | — | 1.0M |
| NanoGPT | $0.15 | $0.6 | $0.015 | 1.0M |
| Poe | $0.21 | $1.8 | $0.021 | 1.1M |
| Jiekou.AI | $0.27 | $2.25 | — | 1.0M |
| Cortecs | $0.299 | $2.491 | $0.029 | 1.0M |
| 302.AI | $0.3 | $2.5 | — | 1.0M |
| Abacus | $0.3 | $2.5 | $0.03 | 1.0M |
| AIHubMix | $0.3 | $2.5 | $0.03 | 1.0M |
| Auriko | $0.3 | $2.5 | $0.03 | 1.0M |
| CrossModel | $0.3 | $2.5 | $0.03 | 1.0M |
| Databricks | $0.3 | $2.5 | $0.03 | 1.0M |
| FastRouter | $0.3 | $2.5 | $0.0375 | 1.0M |
| FrogBot | $0.3 | $2.5 | $0.075 | 1.0M |
| Google | $0.3 | $2.5 | $0.03 | 1.0M |
| Vertex | $0.3 | $2.5 | $0.03 | 1.0M |
| Helicone | $0.3 | $2.5 | $0.075 | 1.0M |
| Impossibl | $0.3 | $2.5 | $0.03 | 1.0M |
| Kilo Gateway | $0.3 | $2.5 | $0.03 | 1.0M |
| DevPass (LLM Gateway) | $0.3 | $2.5 | $0.03 | 1.0M |
| LLM Gateway | $0.3 | $2.5 | $0.03 | 1.0M |
| LLM Gateway | $0.3 | $2.5 | $0.03 | 1.0M |
| Merge Gateway | $0.3 | $2.5 | $0.03 | 1.0M |
| Modelis | $0.3 | $2.5 | — | 1.0M |
| NanoGPT | $0.3 | $2.5 | $0.03 | 1.0M |
| NanoGPT | $0.3 | $2.5 | $0.03 | 1.0M |
| NEAR AI Cloud | $0.3 | $2.5 | $0.03 | 1.0M |
| Ofox | $0.3 | $2.5 | $0.03 | 1.0M |
| OpenRouter | $0.3 | $2.5 | $0.03 | 1.0M |
| OrcaRouter | $0.3 | $2.5 | $0.03 | 1.0M |
| Perplexity Agent | $0.3 | $2.5 | $0.03 | 1.0M |
| Requesty (eu) | $0.3 | $2.5 | $0.075 | 1.0M |
| SAP AI Core | $0.3 | $2.5 | $0.03 | 1.0M |
| Vercel AI Gateway | $0.3 | $2.5 | $0.03 | 1.0M |
| ZenMux | $0.3 | $2.5 | $0.07 | 1.0M |

## Summary

- Cheapest input: $0.09 per 1M tokens (QiHang)
- Cheapest output: $0.6 per 1M tokens (NanoGPT)
- First-party: $2.5 per 1M output tokens (Google)
- Free offers: Kenari
- Subscription plans (not per-token): none
- Released: 2025-06-17
- Inputs: audio, image, pdf, text, video

## FAQ

### What is the cheapest Gemini 2.5 Flash API?

As of Oct 4, 2026, NanoGPT has the lowest Gemini 2.5 Flash output price at $0.6 per 1M tokens, and QiHang has the lowest input price at $0.09 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Gemini 2.5 Flash cost on Google?

Google charges $0.3 per 1M input tokens and $2.5 per 1M output tokens for Gemini 2.5 Flash.

### How many providers offer Gemini 2.5 Flash?

34 providers list Gemini 2.5 Flash on Sovyron; 34 of them sell it at a metered per-token price.

### Is Gemini 2.5 Flash free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### What is the context window of Gemini 2.5 Flash?

Gemini 2.5 Flash supports a 1.1M-token context window and up to 66k output tokens.

HTML page: https://sovyron.com/models/gemini-2-5-flash/
Full dataset: https://sovyron.com/data/catalog.json

---

# Gemini 3.1 Pro Preview API prices

Gemini 3.1 Pro Preview (gemini-pro) — 1.0M context, 66k max output.
33 metered per-token offers from 33 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Kilo Gateway | $1 | $6 | $0.1 | 1.0M |
| 302.AI | $2 | $12 | — | 1.0M |
| Abacus | $2 | $12 | $0.2 | 1.0M |
| AIHubMix | $2 | $12 | $0.2 | 1.0M |
| Auriko | $2 | $12 | $0.2 | 1.0M |
| CrossModel | $2 | $12 | $0.2 | 1.0M |
| DaoXE | $2 | $12 | $0.2 | 1.0M |
| Eden AI | $2 | $12 | $0.2 | 1.0M |
| Eden AI | $2 | $12 | $0.2 | 1.0M |
| FastRouter | $2 | $12 | — | 1.0M |
| FrogBot | $2 | $12 | $0.2 | 1.0M |
| Google | $2 | $12 | $0.2 | 1.0M |
| Vertex | $2 | $12 | $0.2 | 1.0M |
| Impossibl | $2 | $12 | $0.2 | 1.0M |
| DevPass (LLM Gateway) | $2 | $12 | $0.2 | 1.0M |
| LLM Gateway | $2 | $12 | $0.2 | 1.0M |
| LLM Gateway | $2 | $12 | $0.2 | 1.0M |
| Merge Gateway | $2 | $12 | $0.2 | 1.0M |
| NanoGPT | $2 | $12 | $0.2 | 1.0M |
| Ofox | $2 | $12 | $0.2 | 1.0M |
| OpenCode Zen | $2 | $12 | $0.2 | 1.0M |
| OpenRouter | $2 | $12 | $0.2 | 1.0M |
| Opper | $2 | $12 | $0.2 | 1.0M |
| OrcaRouter | $2 | $12 | $0.2 | 1.0M |
| Perplexity Agent | $2 | $12 | $0.2 | 1.0M |
| Pioneer | $2 | $12 | $0.2 | 1.0M |
| Poe | $2 | $12 | $0.2 | 1.0M |
| Requesty | $2 | $12 | $0.2 | 1.0M |
| Tempr Gateway | $2 | $12 | $0.2 | 1.0M |
| Vercel AI Gateway | $2 | $12 | $0.2 | 1.0M |
| Vivgrid | $2 | $12 | $0.2 | 1.0M |
| ZenMux | $2 | $12 | $0.2 | 1.0M |
| Venice AI | $2.5 | $15 | $0.5 | 1.0M |

## Summary

- Cheapest input: $1 per 1M tokens (Kilo Gateway)
- Cheapest output: $6 per 1M tokens (Kilo Gateway)
- First-party: $12 per 1M output tokens (Google)
- Free offers: Kenari
- Subscription plans (not per-token): none
- Released: 2026-02-19
- Inputs: audio, image, pdf, text, video

## FAQ

### What is the cheapest Gemini 3.1 Pro Preview API?

As of Oct 4, 2026, Kilo Gateway has the lowest Gemini 3.1 Pro Preview output price at $6 per 1M tokens, and Kilo Gateway has the lowest input price at $1 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Gemini 3.1 Pro Preview cost on Google?

Google charges $2 per 1M input tokens and $12 per 1M output tokens for Gemini 3.1 Pro Preview.

### How many providers offer Gemini 3.1 Pro Preview?

33 providers list Gemini 3.1 Pro Preview on Sovyron; 33 of them sell it at a metered per-token price.

### Is Gemini 3.1 Pro Preview free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### What is the context window of Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview supports a 1.0M-token context window and up to 66k output tokens.

HTML page: https://sovyron.com/models/gemini-3-1-pro-preview/
Full dataset: https://sovyron.com/data/catalog.json

---

# MiniMax-M2.5 API prices

MiniMax-M2.5 (minimax) — 229k context, 196k max output.
32 metered per-token offers from 41 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| DInference | $0.22 | $0.88 | — | 200k |
| GreenPT | $0.1938 | $1.129 | $0.0627 | 205k |
| Venice AI | $0.27 | $0.95 | $0.03 | 198k |
| OpenRouter | $0.27 | $1.08 | $0.027 | 205k |
| D.Run (China) | $0.29 | $1.16 | — | 205k |
| Cortecs | $0.296 | $1.186 | $0.075 | 196k |
| 302.AI | $0.3 | $1.2 | — | 205k |
| Alibaba (China) | $0.3 | $1.2 | — | 205k |
| Amazon Bedrock | $0.3 | $1.2 | — | 197k |
| CloudFerro Sherlock | $0.3 | $1.2 | — | 196k |
| Eden AI | $0.3 | $1.2 | $0.03 | 205k |
| Friendli | $0.3 | $1.2 | $0.06 | 197k |
| FrogBot | $0.3 | $1.2 | $0.03 | 192k |
| HPC-AI | $0.3 | $1.2 | $0.03 | 196k |
| Hugging Face | $0.3 | $1.2 | $0.03 | 205k |
| Kilo Gateway | $0.3 | $1.2 | $0.03 | 200k |
| DevPass (LLM Gateway) | $0.3 | $1.2 | $0.03 | 229k |
| LLM Gateway | $0.3 | $1.2 | $0.03 | 205k |
| LLM Gateway | $0.3 | $1.2 | $0.03 | 205k |
| Meganova | $0.3 | $1.2 | — | 205k |
| Merge Gateway | $0.3 | $1.2 | $0.03 | 205k |
| MiniMax (minimax.io) | $0.3 | $1.2 | $0.03 | 205k |
| MiniMax (minimax.cn) | $0.3 | $1.2 | $0.03 | 205k |
| NanoGPT | $0.3 | $1.2 | $0.15 | 205k |
| NovitaAI | $0.3 | $1.2 | $0.03 | 205k |
| Ofox | $0.3 | $1.2 | $0.03 | 205k |
| OpenCode Zen | $0.3 | $1.2 | $0.06 | 205k |
| OrcaRouter | $0.3 | $1.2 | $0.03 | 205k |
| TensorX | $0.3 | $1.2 | $0.075 | 197k |
| TokenGo | $0.3 | $1.2 | $0.03 | 205k |
| Vercel AI Gateway | $0.3 | $1.2 | $0.03 | 205k |
| ZenMux | $0.3 | $1.2 | $0.03 | 205k |

## Summary

- Cheapest input: $0.1938 per 1M tokens (GreenPT)
- Cheapest output: $0.88 per 1M tokens (DInference)
- First-party: $1.2 per 1M output tokens (MiniMax (minimax.io))
- Free offers: Alibaba Coding Plan, Alibaba Coding Plan (China), Alibaba Token Plan, Alibaba Token Plan (China), MiniMax Token Plan (minimax.cn), MiniMax Token Plan (minimax.io), SCNet Token Plan, Tencent Coding Plan (China)
- Subscription plans (not per-token): Alibaba Coding Plan, Alibaba Coding Plan (China), Alibaba Token Plan, Alibaba Token Plan (China), MiniMax Token Plan (minimax.cn), MiniMax Token Plan (minimax.io), SCNet Token Plan, Tencent Coding Plan (China)
- Released: 2026-02-12
- Inputs: text

## FAQ

### What is the cheapest MiniMax-M2.5 API?

As of Oct 4, 2026, DInference has the lowest MiniMax-M2.5 output price at $0.88 per 1M tokens, and GreenPT has the lowest input price at $0.1938 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does MiniMax-M2.5 cost on MiniMax (minimax.io)?

MiniMax (minimax.io) charges $0.3 per 1M input tokens and $1.2 per 1M output tokens for MiniMax-M2.5.

### How many providers offer MiniMax-M2.5?

41 providers list MiniMax-M2.5 on Sovyron; 32 of them sell it at a metered per-token price.

### Is MiniMax-M2.5 free?

No provider in the Sovyron catalog lists a free tier for MiniMax-M2.5.

### Is MiniMax-M2.5 included in a subscription plan?

Yes. 6 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of MiniMax-M2.5?

MiniMax-M2.5 supports a 229k-token context window and up to 196k output tokens.

HTML page: https://sovyron.com/models/minimax-m2-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5 API prices

GPT-5 (gpt) — 400k context, 128k max output.
31 metered per-token offers from 34 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $1 | $8 | $0.104 | 400k |
| OpenCode Zen | $1.07 | $8.5 | $0.107 | 400k |
| Poe | $1.1 | $9 | $0.11 | 400k |
| 302.AI | $1.25 | $10 | — | 400k |
| Abacus | $1.25 | $10 | $0.125 | 400k |
| AIHubMix | $1.25 | $10 | $0.125 | 400k |
| Azure | $1.25 | $10 | $0.13 | 400k |
| Azure Cognitive Services | $1.25 | $10 | $0.13 | 400k |
| Cloudflare AI Gateway | $1.25 | $10 | $0.125 | 128k |
| Databricks | $1.25 | $10 | $0.125 | 400k |
| DigitalOcean | $1.25 | $10 | $0.125 | 400k |
| Eden AI | $1.25 | $10 | $0.125 | 400k |
| FastRouter | $1.25 | $10 | $0.125 | 400k |
| Helicone | $1.25 | $10 | $0.125 | 400k |
| Impossibl | $1.25 | $10 | $0.125 | 400k |
| Kilo Gateway | $1.25 | $10 | $0.125 | 400k |
| DevPass (LLM Gateway) | $1.25 | $10 | $0.125 | 400k |
| LLM Gateway | $1.25 | $10 | $0.125 | 400k |
| LLM Gateway | $1.25 | $10 | $0.125 | 400k |
| Merge Gateway | $1.25 | $10 | $0.125 | 400k |
| NanoGPT | $1.25 | $10 | $0.125 | 400k |
| NEAR AI Cloud | $1.25 | $10 | $0.125 | 400k |
| Neon | $1.25 | $10 | $0.125 | 400k |
| OpenAI | $1.25 | $10 | $0.125 | 400k |
| OpenRouter | $1.25 | $10 | $0.125 | 400k |
| OrcaRouter | $1.25 | $10 | $0.125 | 400k |
| SAP AI Core | $1.25 | $10 | $0.125 | 400k |
| Vercel AI Gateway | $1.25 | $10 | $0.125 | 400k |
| ZenMux | $1.25 | $10 | $0.12 | 400k |
| Cortecs | $1.375 | $10.96 | $0.156 | 400k |
| Requesty (eu) | $1.375 | $11 | $0.1375 | 400k |

## Summary

- Cheapest input: $1 per 1M tokens (Ofox)
- Cheapest output: $8 per 1M tokens (Ofox)
- First-party: $10 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-08-07
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5 API?

As of Oct 4, 2026, Ofox has the lowest GPT-5 output price at $8 per 1M tokens, and Ofox has the lowest input price at $1 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5 cost on OpenAI?

OpenAI charges $1.25 per 1M input tokens and $10 per 1M output tokens for GPT-5.

### How many providers offer GPT-5?

34 providers list GPT-5 on Sovyron; 31 of them sell it at a metered per-token price.

### Is GPT-5 free?

No provider in the Sovyron catalog lists a free tier for GPT-5.

### What is the context window of GPT-5?

GPT-5 supports a 400k-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.2 API prices

GPT-5.2 (gpt) — 400k context, 128k max output.
32 metered per-token offers from 33 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| QiHang | $0.25 | $2 | — | 400k |
| UnoRouter | $1.05 | $8.4 | — | 400k |
| SAP AI Core | $1.25 | $9.44 | $0.12 | 400k |
| Ofox | $1.4 | $11.2 | $0.144 | 400k |
| Jiekou.AI | $1.575 | $12.6 | — | 400k |
| Poe | $1.6 | $13 | $0.16 | 400k |
| 302.AI | $1.75 | $14 | — | 400k |
| Abacus | $1.75 | $14 | $0.175 | 400k |
| AIHubMix | $1.75 | $14 | $0.175 | 400k |
| Azure | $1.75 | $14 | $0.125 | 400k |
| Azure Cognitive Services | $1.75 | $14 | $0.125 | 400k |
| Databricks | $1.75 | $14 | $0.175 | 400k |
| DigitalOcean | $1.75 | $14 | $0.175 | 400k |
| Eden AI | $1.75 | $14 | $0.175 | 400k |
| Impossibl | $1.75 | $14 | $0.175 | 400k |
| Kilo Gateway | $1.75 | $14 | $0.175 | 400k |
| DevPass (LLM Gateway) | $1.75 | $14 | $0.175 | 400k |
| LLM Gateway | $1.75 | $14 | $0.175 | 400k |
| LLM Gateway | $1.75 | $14 | $0.175 | 400k |
| Merge Gateway | $1.75 | $14 | $0.175 | 400k |
| NanoGPT | $1.75 | $14 | $0.175 | 400k |
| NEAR AI Cloud | $1.75 | $14 | $0.175 | 400k |
| Neon | $1.75 | $14 | $0.175 | 400k |
| OpenAI | $1.75 | $14 | $0.175 | 400k |
| OpenCode Zen | $1.75 | $14 | $0.175 | 400k |
| OpenRouter | $1.75 | $14 | $0.175 | 400k |
| OrcaRouter | $1.75 | $14 | $0.175 | 400k |
| Perplexity Agent | $1.75 | $14 | $0.175 | 400k |
| Vercel AI Gateway | $1.75 | $14 | $0.175 | 400k |
| ZenMux | $1.75 | $14 | $0.17 | 400k |
| Venice AI | $2.19 | $17.5 | $0.219 | 256k |
| Vercel AI Gateway | $21 | $168 | — | 400k |

## Summary

- Cheapest input: $0.25 per 1M tokens (QiHang)
- Cheapest output: $2 per 1M tokens (QiHang)
- First-party: $14 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-12-11
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.2 API?

As of Oct 4, 2026, QiHang has the lowest GPT-5.2 output price at $2 per 1M tokens, and QiHang has the lowest input price at $0.25 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5.2 cost on OpenAI?

OpenAI charges $1.75 per 1M input tokens and $14 per 1M output tokens for GPT-5.2.

### How many providers offer GPT-5.2?

33 providers list GPT-5.2 on Sovyron; 32 of them sell it at a metered per-token price.

### Is GPT-5.2 free?

No provider in the Sovyron catalog lists a free tier for GPT-5.2.

### What is the context window of GPT-5.2?

GPT-5.2 supports a 400k-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-2/
Full dataset: https://sovyron.com/data/catalog.json

---

# Gemini 2.5 Pro API prices

Gemini 2.5 Pro (gemini-pro) — 1.1M context, 66k max output.
31 metered per-token offers from 32 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Poe | $0.87 | $7 | $0.087 | 1.1M |
| Jiekou.AI | $1.125 | $9 | — | 1.0M |
| 302.AI | $1.25 | $10 | — | 1.0M |
| Abacus | $1.25 | $10 | $0.125 | 1.0M |
| AIHubMix | $1.25 | $10 | $0.125 | 1.0M |
| Auriko | $1.25 | $10 | $0.125 | 1.0M |
| CrossModel | $1.25 | $10 | $0.125 | 1.0M |
| Databricks | $1.25 | $10 | $0.125 | 1.0M |
| FastRouter | $1.25 | $10 | $0.31 | 1.0M |
| FrogBot | $1.25 | $10 | $0.31 | 1.0M |
| Google | $1.25 | $10 | $0.125 | 1.0M |
| Vertex | $1.25 | $10 | $0.125 | 1.0M |
| Helicone | $1.25 | $10 | $0.3125 | 1.0M |
| Impossibl | $1.25 | $10 | $0.125 | 1.0M |
| Kilo Gateway | $1.25 | $10 | $0.125 | 1.0M |
| DevPass (LLM Gateway) | $1.25 | $10 | $0.125 | 1.0M |
| LLM Gateway | $1.25 | $10 | $0.125 | 1.0M |
| LLM Gateway | $1.25 | $10 | $0.125 | 1.0M |
| Merge Gateway | $1.25 | $10 | $0.125 | 1.0M |
| Modelis | $1.25 | $10 | — | 1.0M |
| NanoGPT | $1.25 | $10 | $0.125 | 1.0M |
| NEAR AI Cloud | $1.25 | $10 | $0.125 | 1.0M |
| Ofox | $1.25 | $10 | $0.125 | 1.0M |
| OpenRouter | $1.25 | $10 | $0.125 | 1.0M |
| OrcaRouter | $1.25 | $10 | $0.125 | 1.0M |
| Perplexity Agent | $1.25 | $10 | $0.125 | 1.0M |
| Requesty (eu) | $1.25 | $10 | $0.31 | 1.0M |
| SAP AI Core | $1.25 | $10 | $0.125 | 1.0M |
| Vercel AI Gateway | $1.25 | $10 | $0.125 | 1.0M |
| ZenMux | $1.25 | $10 | $0.31 | 1.0M |
| Cortecs | $1.495 | $9.964 | $0.242 | 1.0M |

## Summary

- Cheapest input: $0.87 per 1M tokens (Poe)
- Cheapest output: $7 per 1M tokens (Poe)
- First-party: $10 per 1M output tokens (Google)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-06-17
- Inputs: audio, image, pdf, text, video

## FAQ

### What is the cheapest Gemini 2.5 Pro API?

As of Oct 4, 2026, Poe has the lowest Gemini 2.5 Pro output price at $7 per 1M tokens, and Poe has the lowest input price at $0.87 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Gemini 2.5 Pro cost on Google?

Google charges $1.25 per 1M input tokens and $10 per 1M output tokens for Gemini 2.5 Pro.

### How many providers offer Gemini 2.5 Pro?

32 providers list Gemini 2.5 Pro on Sovyron; 31 of them sell it at a metered per-token price.

### Is Gemini 2.5 Pro free?

No provider in the Sovyron catalog lists a free tier for Gemini 2.5 Pro.

### What is the context window of Gemini 2.5 Pro?

Gemini 2.5 Pro supports a 1.1M-token context window and up to 66k output tokens.

HTML page: https://sovyron.com/models/gemini-2-5-pro/
Full dataset: https://sovyron.com/data/catalog.json

---

# DeepSeek V3.2 API prices

DeepSeek V3.2 (deepseek) — 164k context, 164k max output.
31 metered per-token offers from 32 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| CrofAI | $0.18 | $0.35 | $0.04 | 164k |
| TokenGo | $0.2174 | $0.326 | $0.06 | 128k |
| Deep Infra | $0.26 | $0.38 | $0.13 | 164k |
| DevPass (LLM Gateway) | $0.26 | $0.38 | $0.13 | 164k |
| LLM Gateway | $0.26 | $0.38 | $0.13 | 160k |
| Meganova | $0.26 | $0.38 | — | 164k |
| LLM Gateway | $0.269 | $0.4 | $0.1345 | 164k |
| NovitaAI | $0.269 | $0.4 | $0.1345 | 164k |
| Abacus | $0.27 | $0.4 | — | 128k |
| Poe | $0.27 | $0.4 | $0.13 | 128k |
| Helicone | $0.27 | $0.41 | — | 164k |
| Hugging Face | $0.28 | $0.4 | — | 164k |
| Merge Gateway | $0.28 | $0.4 | $0.13 | 128k |
| Kilo Gateway | $0.28 | $0.42 | $0.028 | 131k |
| NanoGPT | $0.28 | $0.42 | $0.14 | 163k |
| OpenRouter | $0.28 | $0.42 | $0.028 | 164k |
| Vivgrid | $0.28 | $0.42 | — | 128k |
| ZenMux | $0.28 | $0.43 | — | 128k |
| 302.AI | $0.29 | $0.43 | — | 128k |
| Ofox | $0.29 | $0.43 | $0.06 | 128k |
| Cortecs | $0.296 | $0.495 | $0.075 | 164k |
| TensorX | $0.3 | $0.5 | $0.075 | 164k |
| Venice AI | $0.33 | $0.48 | $0.16 | 160k |
| Melious | $0.3478 | $0.5796 | $0.0927 | 164k |
| Friendli | $0.5 | $1.5 | $0.25 | 164k |
| LLM Gateway | $0.56 | $1.68 | $0.056 | 164k |
| Azure | $0.58 | $1.68 | — | 128k |
| Azure Cognitive Services | $0.58 | $1.68 | — | 128k |
| EmpirioLabs AI | $0.57 | $1.71 | $0.57 | 128k |
| Amazon Bedrock | $0.62 | $1.85 | — | 164k |
| Vercel AI Gateway | $0.62 | $1.85 | — | 128k |

## Summary

- Cheapest input: $0.18 per 1M tokens (CrofAI)
- Cheapest output: $0.326 per 1M tokens (TokenGo)
- First-party: not listed separately
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China)
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China)
- Released: 2025-12-01
- Inputs: image, pdf, text

## FAQ

### What is the cheapest DeepSeek V3.2 API?

As of Oct 4, 2026, TokenGo has the lowest DeepSeek V3.2 output price at $0.326 per 1M tokens, and CrofAI has the lowest input price at $0.18 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer DeepSeek V3.2?

32 providers list DeepSeek V3.2 on Sovyron; 31 of them sell it at a metered per-token price.

### Is DeepSeek V3.2 free?

No provider in the Sovyron catalog lists a free tier for DeepSeek V3.2.

### Is DeepSeek V3.2 included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of DeepSeek V3.2?

DeepSeek V3.2 supports a 164k-token context window and up to 164k output tokens.

HTML page: https://sovyron.com/models/deepseek-v3-2/
Full dataset: https://sovyron.com/data/catalog.json

---

# GLM-4.7 API prices

GLM-4.7 (glm) — 205k context, 200k max output.
33 metered per-token offers from 34 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Meganova | $0.2 | $0.8 | — | 203k |
| AIHubMix | $0.274 | $1.0959 | $0.0548 | 205k |
| 302.AI | $0.286 | $1.142 | — | 205k |
| ZenMux | $0.2911 | $1.1645 | $0.0582 | 200k |
| Deep Infra | $0.4 | $1.75 | $0.08 | 203k |
| DInference | $0.45 | $1.65 | — | 200k |
| DevPass (LLM Gateway) | $0.38 | $1.98 | $0.19 | 205k |
| NanoGPT | $0.4004 | $1.9292 | $0.0801 | 200k |
| LLM Gateway | $0.45 | $2 | — | 203k |
| Ofox | $0.4 | $2.2 | $0.11 | 205k |
| CrossModel | $0.47 | $2.16 | $0.1 | 200k |
| Abacus | $0.6 | $2.2 | — | 205k |
| Amazon Bedrock | $0.6 | $2.2 | — | 203k |
| Baseten | $0.6 | $2.2 | $0.12 | 200k |
| Eden AI | $0.6 | $2.2 | $0.11 | 203k |
| Hugging Face | $0.6 | $2.2 | $0.11 | 205k |
| Impossibl | $0.6 | $2.2 | $0.11 | 205k |
| Jiekou.AI | $0.6 | $2.2 | — | 205k |
| Kilo Gateway | $0.6 | $2.2 | $0.11 | 203k |
| LLM Gateway | $0.6 | $2.2 | $0.11 | 205k |
| LLM Gateway | $0.6 | $2.2 | — | 203k |
| LLM Gateway | $0.6 | $2.2 | $0.11 | 200k |
| Merge Gateway | $0.6 | $2.2 | $0.11 | 200k |
| NovitaAI | $0.6 | $2.2 | $0.11 | 205k |
| OpenRouter | $0.6 | $2.2 | $0.11 | 205k |
| OrcaRouter | $0.6 | $2.2 | $0.11 | 205k |
| Tempr Gateway | $0.6 | $2.2 | $0.11 | 205k |
| Vercel AI Gateway | $0.6 | $2.2 | — | 200k |
| Z.AI | $0.6 | $2.2 | $0.11 | 205k |
| Zhipu AI | $0.6 | $2.2 | $0.11 | 205k |
| Venice AI | $0.55 | $2.65 | $0.11 | 198k |
| LLM Gateway | $2.25 | $2.75 | — | 200k |
| Moark | $3.5 | $14 | — | 205k |

## Summary

- Cheapest input: $0.2 per 1M tokens (Meganova)
- Cheapest output: $0.8 per 1M tokens (Meganova)
- First-party: $2.2 per 1M output tokens (Z.AI)
- Free offers: Alibaba Coding Plan, Alibaba Coding Plan (China), KUAE Cloud Coding Plan, Z.AI Coding Plan
- Subscription plans (not per-token): Alibaba Coding Plan, Alibaba Coding Plan (China), KUAE Cloud Coding Plan, Z.AI Coding Plan
- Released: 2025-12-22
- Inputs: text

## FAQ

### What is the cheapest GLM-4.7 API?

As of Oct 4, 2026, Meganova has the lowest GLM-4.7 output price at $0.8 per 1M tokens, and Meganova has the lowest input price at $0.2 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GLM-4.7 cost on Z.AI?

Z.AI charges $0.6 per 1M input tokens and $2.2 per 1M output tokens for GLM-4.7.

### How many providers offer GLM-4.7?

34 providers list GLM-4.7 on Sovyron; 33 of them sell it at a metered per-token price.

### Is GLM-4.7 free?

No provider in the Sovyron catalog lists a free tier for GLM-4.7.

### Is GLM-4.7 included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is Z.ai GLM Coding Lite at $18/month.

### What is the context window of GLM-4.7?

GLM-4.7 supports a 205k-token context window and up to 200k output tokens.

HTML page: https://sovyron.com/models/glm-4-7/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5 Nano API prices

GPT-5 Nano (gpt-nano) — 400k context, 128k max output.
30 metered per-token offers from 30 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $0.04 | $0.32 | $0.008 | 400k |
| Jiekou.AI | $0.045 | $0.36 | — | 400k |
| Poe | $0.045 | $0.36 | $0.0045 | 400k |
| Helicone | $0.05 | $0.4 | $0.005 | 400k |
| Abacus | $0.05 | $0.4 | $0.005 | 400k |
| Azure | $0.05 | $0.4 | $0.01 | 400k |
| Azure Cognitive Services | $0.05 | $0.4 | $0.01 | 400k |
| Cloudflare AI Gateway | $0.05 | $0.4 | $0.005 | 128k |
| Databricks | $0.05 | $0.4 | $0.005 | 400k |
| DigitalOcean | $0.05 | $0.4 | $0.005 | 400k |
| Eden AI | $0.05 | $0.4 | $0.005 | 400k |
| FastRouter | $0.05 | $0.4 | $0.005 | 400k |
| Impossibl | $0.05 | $0.4 | $0.005 | 400k |
| Kilo Gateway | $0.05 | $0.4 | $0.005 | 400k |
| DevPass (LLM Gateway) | $0.05 | $0.4 | $0.005 | 400k |
| LLM Gateway | $0.05 | $0.4 | $0.005 | 400k |
| LLM Gateway | $0.05 | $0.4 | $0.005 | 400k |
| Merge Gateway | $0.05 | $0.4 | $0.005 | 400k |
| NanoGPT | $0.05 | $0.4 | $0.005 | 400k |
| NEAR AI Cloud | $0.05 | $0.4 | $0.005 | 400k |
| Neon | $0.05 | $0.4 | $0.005 | 400k |
| OpenAI | $0.05 | $0.4 | $0.005 | 400k |
| OpenCode Zen | $0.05 | $0.4 | $0.005 | 400k |
| OpenRouter | $0.05 | $0.4 | $0.005 | 400k |
| OrcaRouter | $0.05 | $0.4 | $0.005 | 400k |
| Pioneer | $0.05 | $0.4 | $0.005 | 400k |
| SAP AI Core | $0.05 | $0.4 | $0.005 | 400k |
| Vercel AI Gateway | $0.05 | $0.4 | $0.005 | 400k |
| Requesty (eu) | $0.055 | $0.44 | $0.0055 | 200k |
| Cortecs | $0.06 | $0.439 | $0.019 | 400k |

## Summary

- Cheapest input: $0.04 per 1M tokens (Ofox)
- Cheapest output: $0.32 per 1M tokens (Ofox)
- First-party: $0.4 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-08-07
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5 Nano API?

As of Oct 4, 2026, Ofox has the lowest GPT-5 Nano output price at $0.32 per 1M tokens, and Ofox has the lowest input price at $0.04 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5 Nano cost on OpenAI?

OpenAI charges $0.05 per 1M input tokens and $0.4 per 1M output tokens for GPT-5 Nano.

### How many providers offer GPT-5 Nano?

30 providers list GPT-5 Nano on Sovyron; 30 of them sell it at a metered per-token price.

### Is GPT-5 Nano free?

No provider in the Sovyron catalog lists a free tier for GPT-5 Nano.

### What is the context window of GPT-5 Nano?

GPT-5 Nano supports a 400k-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-nano/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.1 API prices

GPT-5.1 (gpt) — 400k context, 131k max output.
31 metered per-token offers from 31 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $1 | $8 | $0.104 | 400k |
| OpenCode Zen | $1.07 | $8.5 | $0.107 | 400k |
| Poe | $1.1 | $9 | $0.11 | 400k |
| Jiekou.AI | $1.125 | $9 | — | 400k |
| 302.AI | $1.25 | $10 | — | 400k |
| Abacus | $1.25 | $10 | $0.125 | 400k |
| AIHubMix | $1.25 | $10 | $0.13 | 400k |
| Azure | $1.25 | $10 | $0.125 | 400k |
| Azure Cognitive Services | $1.25 | $10 | $0.125 | 400k |
| Cloudflare AI Gateway | $1.25 | $10 | $0.125 | 128k |
| Databricks | $1.25 | $10 | $0.125 | 400k |
| Eden AI | $1.25 | $10 | $0.125 | 400k |
| Helicone | $1.25 | $10 | $0.125 | 400k |
| Impossibl | $1.25 | $10 | $0.125 | 400k |
| Kilo Gateway | $1.25 | $10 | $0.125 | 400k |
| DevPass (LLM Gateway) | $1.25 | $10 | $0.125 | 400k |
| LLM Gateway | $1.25 | $10 | $0.125 | 400k |
| LLM Gateway | $1.25 | $10 | $0.125 | 400k |
| Merge Gateway | $1.25 | $10 | $0.125 | 400k |
| NanoGPT | $1.25 | $10 | $0.125 | 400k |
| NanoGPT | $1.25 | $10 | $0.125 | 400k |
| NEAR AI Cloud | $1.25 | $10 | $0.125 | 400k |
| Neon | $1.25 | $10 | $0.125 | 400k |
| OpenAI | $1.25 | $10 | $0.125 | 400k |
| OpenRouter | $1.25 | $10 | $0.125 | 400k |
| OrcaRouter | $1.25 | $10 | $0.125 | 400k |
| Perplexity Agent | $1.25 | $10 | $0.125 | 400k |
| Pioneer | $1.25 | $10 | $0.125 | 400k |
| ZenMux | $1.25 | $10 | $0.12 | 400k |
| Cortecs | $1.375 | $10.96 | $0.156 | 400k |
| Requesty (eu) | $1.375 | $11 | $0.1375 | 400k |

## Summary

- Cheapest input: $1 per 1M tokens (Ofox)
- Cheapest output: $8 per 1M tokens (Ofox)
- First-party: $10 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-11-13
- Inputs: audio, image, pdf, text

## FAQ

### What is the cheapest GPT-5.1 API?

As of Oct 4, 2026, Ofox has the lowest GPT-5.1 output price at $8 per 1M tokens, and Ofox has the lowest input price at $1 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5.1 cost on OpenAI?

OpenAI charges $1.25 per 1M input tokens and $10 per 1M output tokens for GPT-5.1.

### How many providers offer GPT-5.1?

31 providers list GPT-5.1 on Sovyron; 31 of them sell it at a metered per-token price.

### Is GPT-5.1 free?

No provider in the Sovyron catalog lists a free tier for GPT-5.1.

### What is the context window of GPT-5.1?

GPT-5.1 supports a 400k-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/gpt-5-1/
Full dataset: https://sovyron.com/data/catalog.json

---

# Gemini 3 Flash Preview API prices

Gemini 3 Flash Preview (gemini-flash) — 1.0M context, 66k max output.
31 metered per-token offers from 30 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| QiHang | $0.07 | $0.43 | — | 1.0M |
| Kilo Gateway | $0.25 | $1.5 | $0.025 | 1.0M |
| Poe | $0.4 | $2.4 | $0.04 | 1.0M |
| 302.AI | $0.5 | $3 | — | 1.0M |
| Abacus | $0.5 | $3 | $0.05 | 1.0M |
| AIHubMix | $0.5 | $3 | $0.05 | 1.0M |
| CrossModel | $0.5 | $3 | $0.05 | 1.0M |
| Databricks | $0.5 | $3 | $0.05 | 1.0M |
| Eden AI | $0.5 | $3 | $0.05 | 1.0M |
| Eden AI | $0.5 | $3 | $0.05 | 1.0M |
| FrogBot | $0.5 | $3 | $0.05 | 1.0M |
| Google | $0.5 | $3 | $0.05 | 1.0M |
| Vertex | $0.5 | $3 | $0.05 | 1.0M |
| Jiekou.AI | $0.5 | $3 | — | 1.0M |
| DevPass (LLM Gateway) | $0.5 | $3 | $0.05 | 1.0M |
| LLM Gateway | $0.5 | $3 | $0.05 | 1.0M |
| LLM Gateway | $0.5 | $3 | $0.05 | 1.0M |
| Merge Gateway | $0.5 | $3 | $0.05 | 1.0M |
| NanoGPT | $0.5 | $3 | $0.05 | 1.0M |
| Neon | $0.5 | $3 | $0.05 | 1.0M |
| Ofox | $0.5 | $3 | $0.05 | 1.0M |
| OpenCode Zen | $0.5 | $3 | $0.05 | 1.0M |
| OpenRouter | $0.5 | $3 | $0.05 | 1.0M |
| Opper | $0.5 | $3 | $0.05 | 1.0M |
| OrcaRouter | $0.5 | $3 | $0.05 | 1.0M |
| Perplexity Agent | $0.5 | $3 | $0.05 | 1.0M |
| Pioneer | $0.5 | $3 | $0.05 | 1.0M |
| Tempr Gateway | $0.5 | $3 | $0.05 | 1.0M |
| Vercel AI Gateway | $0.5 | $3 | $0.05 | 1.0M |
| ZenMux | $0.5 | $3 | $0.05 | 1.0M |
| Venice AI | $0.7 | $3.75 | $0.07 | 256k |

## Summary

- Cheapest input: $0.07 per 1M tokens (QiHang)
- Cheapest output: $0.43 per 1M tokens (QiHang)
- First-party: $3 per 1M output tokens (Google)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-12-17
- Inputs: audio, image, pdf, text, video

## FAQ

### What is the cheapest Gemini 3 Flash Preview API?

As of Oct 4, 2026, QiHang has the lowest Gemini 3 Flash Preview output price at $0.43 per 1M tokens, and QiHang has the lowest input price at $0.07 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Gemini 3 Flash Preview cost on Google?

Google charges $0.5 per 1M input tokens and $3 per 1M output tokens for Gemini 3 Flash Preview.

### How many providers offer Gemini 3 Flash Preview?

30 providers list Gemini 3 Flash Preview on Sovyron; 31 of them sell it at a metered per-token price.

### Is Gemini 3 Flash Preview free?

No provider in the Sovyron catalog lists a free tier for Gemini 3 Flash Preview.

### What is the context window of Gemini 3 Flash Preview?

Gemini 3 Flash Preview supports a 1.0M-token context window and up to 66k output tokens.

HTML page: https://sovyron.com/models/gemini-3-flash-preview/
Full dataset: https://sovyron.com/data/catalog.json

---

# Grok 4.3 API prices

Grok 4.3 (grok) — 1.0M context, 1.0M max output.
31 metered per-token offers from 30 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| 302.AI | $1.25 | $2.5 | — | 1.0M |
| Abacus | $1.25 | $2.5 | $0.2 | 1.0M |
| AIHubMix | $1.25 | $2.5 | $0.2 | 1.0M |
| Amazon Bedrock | $1.25 | $2.5 | $0.2 | 1.0M |
| Auriko | $1.25 | $2.5 | $0.2 | 1.0M |
| Cloudflare AI Gateway | $1.25 | $2.5 | $0.2 | 1.0M |
| CrossModel | $1.25 | $2.5 | $0.2 | 1.0M |
| DaoXE | $1.25 | $2.5 | $0.2 | 1.0M |
| Eden AI | $1.25 | $2.5 | $0.2 | 1.0M |
| FastRouter | $1.25 | $2.5 | — | 1.0M |
| FrogBot | $1.25 | $2.5 | $0.2 | 1.0M |
| Vertex | $1.25 | $2.5 | $0.2 | 200k |
| Impossibl | $1.25 | $2.5 | $0.2 | 1.0M |
| Kilo Gateway | $1.25 | $2.5 | $0.2 | 1.0M |
| DevPass (LLM Gateway) | $1.25 | $2.5 | $0.2 | 1.0M |
| LLM Gateway | $1.25 | $2.5 | $0.2 | 1.0M |
| LLM Gateway | $1.25 | $2.5 | $0.2 | 20k |
| LLM Gateway | $1.25 | $2.5 | $0.2 | 1.0M |
| Merge Gateway | $1.25 | $2.5 | $0.2 | 1.0M |
| NanoGPT | $1.25 | $2.5 | $0.2 | 1.0M |
| OCI Generative AI | $1.25 | $2.5 | $0.2 | 1.0M |
| Ofox | $1.25 | $2.5 | $0.2 | 1.0M |
| OpenRouter | $1.25 | $2.5 | $0.2 | 1.0M |
| Opper | $1.25 | $2.5 | $0.2 | 1.0M |
| OrcaRouter | $1.25 | $2.5 | $0.2 | 1.0M |
| Requesty | $1.25 | $2.5 | $0.2 | 1.0M |
| Tempr Gateway | $1.25 | $2.5 | $0.2 | 1.0M |
| Vercel AI Gateway | $1.25 | $2.5 | $0.2 | 1.0M |
| xAI | $1.25 | $2.5 | $0.2 | 1.0M |
| ZenMux | $1.25 | $2.5 | $0.2 | 1.0M |
| Venice AI | $1.42 | $2.83 | $0.23 | 1.0M |

## Summary

- Cheapest input: $1.25 per 1M tokens (302.AI)
- Cheapest output: $2.5 per 1M tokens (302.AI)
- First-party: $2.5 per 1M output tokens (xAI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-04-17
- Inputs: image, pdf, text, video

## FAQ

### What is the cheapest Grok 4.3 API?

As of Oct 4, 2026, 302.AI has the lowest Grok 4.3 output price at $2.5 per 1M tokens, and 302.AI has the lowest input price at $1.25 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Grok 4.3 cost on xAI?

xAI charges $1.25 per 1M input tokens and $2.5 per 1M output tokens for Grok 4.3.

### How many providers offer Grok 4.3?

30 providers list Grok 4.3 on Sovyron; 31 of them sell it at a metered per-token price.

### Is Grok 4.3 free?

No provider in the Sovyron catalog lists a free tier for Grok 4.3.

### What is the context window of Grok 4.3?

Grok 4.3 supports a 1.0M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/grok-4-3/
Full dataset: https://sovyron.com/data/catalog.json

---

# Llama-3.3-70B-Instruct API prices

Llama-3.3-70B-Instruct (llama) — 131k context, 131k max output.
32 metered per-token offers from 33 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| NanoGPT | $0.05 | $0.23 | $0.025 | 131k |
| Meganova | $0.1 | $0.3 | — | 131k |
| Eden AI | $0.1 | $0.32 | — | 131k |
| Kilo Gateway | $0.1 | $0.32 | — | 131k |
| IO.NET | $0.13 | $0.38 | $0.065 | 128k |
| Helicone | $0.13 | $0.39 | — | 128k |
| DevPass (LLM Gateway) | $0.135 | $0.4 | — | 131k |
| LLM Gateway | $0.135 | $0.4 | — | 131k |
| NovitaAI | $0.135 | $0.4 | — | 131k |
| Merge Gateway | $0.22 | $0.5 | $0.11 | 131k |
| OpenRouter | $0.22 | $0.5 | $0.11 | 131k |
| Crusoe | $0.25 | $0.75 | $0.13 | 128k |
| Abacus | $0.59 | $0.79 | — | 131k |
| Hugging Face | $0.59 | $0.79 | — | 131k |
| DigitalOcean | $0.65 | $0.65 | — | 128k |
| Azure | $0.71 | $0.71 | — | 128k |
| Azure Cognitive Services | $0.71 | $0.71 | — | 128k |
| Amazon Bedrock | $0.72 | $0.72 | — | 128k |
| Amazon Bedrock (us) | $0.72 | $0.72 | — | 128k |
| OCI Generative AI | $0.72 | $0.72 | — | 128k |
| Cortecs | $0.724 | $0.724 | — | 131k |
| Neon | $0.5 | $1.5 | — | 128k |
| watsonx.ai | $0.7526 | $0.7526 | — | 131k |
| Pioneer | $0.9 | $0.9 | $0.9 | 16k |
| Scaleway | $0.9 | $0.9 | — | 100k |
| LLM Gateway | $0.85 | $1.2 | — | 128k |
| Eden AI | $1.0103 | $1.0103 | — | 128k |
| Regolo AI | $0.6 | $2.7 | — | 128k |
| evroc | $1.15 | $1.15 | — | 128k |
| GreenPT | $1.254 | $1.254 | — | 100k |
| Tinfoil | $1.75 | $2.75 | — | 131k |
| CloudFerro Sherlock | $2.92 | $2.92 | — | 70k |

## Summary

- Cheapest input: $0.05 per 1M tokens (NanoGPT)
- Cheapest output: $0.23 per 1M tokens (NanoGPT)
- First-party: not listed separately
- Free offers: Llama, Pendra, Vercel AI Gateway
- Subscription plans (not per-token): none
- Released: 2024-12-06
- Inputs: text

## FAQ

### What is the cheapest Llama-3.3-70B-Instruct API?

As of Oct 4, 2026, NanoGPT has the lowest Llama-3.3-70B-Instruct output price at $0.23 per 1M tokens, and NanoGPT has the lowest input price at $0.05 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Llama-3.3-70B-Instruct?

33 providers list Llama-3.3-70B-Instruct on Sovyron; 32 of them sell it at a metered per-token price.

### Is Llama-3.3-70B-Instruct free?

3 provider(s) list a free-tier offer: Llama, Pendra, Vercel AI Gateway. Free tiers usually have rate limits.

### What is the context window of Llama-3.3-70B-Instruct?

Llama-3.3-70B-Instruct supports a 131k-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/llama-3-3-70b-instruct/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Fable 5.1 API prices

Claude Fable 5.1 (claude-fable) — 1.0M context, 128k max output.
33 metered per-token offers from 29 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| 302.AI | $10 | $50 | — | 1.0M |
| Amazon Bedrock | $10 | $50 | $0.25 | 1.0M |
| Amazon Bedrock (global) | $10 | $50 | $0.25 | 1.0M |
| Anthropic | $10 | $50 | $0.25 | 1.0M |
| Azure | $10 | $50 | $0.25 | 1.0M |
| Azure Cognitive Services | $10 | $50 | $0.25 | 1.0M |
| Cloudflare AI Gateway | $10 | $50 | $0.25 | 1.0M |
| CrossModel | $10 | $50 | $0.25 | 1.0M |
| DigitalOcean | $10 | $50 | $0.25 | 1.0M |
| Eden AI | $10 | $50 | $0.25 | 1.0M |
| Vertex | $10 | $50 | $0.25 | 1.0M |
| Vertex (Anthropic) | $10 | $50 | $0.25 | 1.0M |
| Kilo Gateway | $10 | $50 | $0.25 | 1.0M |
| DevPass (LLM Gateway) | $10 | $50 | $0.25 | 1.0M |
| LLM Gateway | $10 | $50 | $0.25 | 1.0M |
| LLM Gateway | $10 | $50 | $0.25 | 1.0M |
| LLM Gateway | $10 | $50 | $0.25 | 1.0M |
| Merge Gateway | $10 | $50 | $0.25 | 1.0M |
| NanoGPT | $10 | $50 | $0.25 | 1.0M |
| Neon | $10 | $50 | $0.25 | 1.0M |
| Ofox | $10 | $50 | $0.25 | 1.0M |
| OpenCode Zen | $10 | $50 | $0.25 | 1.0M |
| OpenRouter | $10 | $50 | $0.25 | 1.0M |
| Opper | $10 | $50 | $0.25 | 1.0M |
| Requesty | $10 | $50 | $0.25 | 1.0M |
| Tempr Gateway | $10 | $50 | $0.25 | 1.0M |
| Vercel AI Gateway | $10 | $50 | $0.25 | 1.0M |
| Vivgrid | $10 | $50 | $0.5 | 1.0M |
| ZenMux | $10 | $50 | $0.25 | 1.0M |
| AIHubMix | $11 | $55 | $0.275 | 1.0M |
| Amazon Bedrock (us) | $11 | $55 | $0.275 | 1.0M |
| Requesty (eu) | $11 | $55 | $0.275 | 1.0M |
| Venice AI | $12 | $60 | $0.3 | 1.0M |

## Summary

- Cheapest input: $10 per 1M tokens (302.AI)
- Cheapest output: $50 per 1M tokens (302.AI)
- First-party: $50 per 1M output tokens (Anthropic)
- Free offers: none
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-09-01
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Fable 5.1 API?

As of Oct 4, 2026, 302.AI has the lowest Claude Fable 5.1 output price at $50 per 1M tokens, and 302.AI has the lowest input price at $10 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Claude Fable 5.1 cost on Anthropic?

Anthropic charges $10 per 1M input tokens and $50 per 1M output tokens for Claude Fable 5.1.

### How many providers offer Claude Fable 5.1?

29 providers list Claude Fable 5.1 on Sovyron; 33 of them sell it at a metered per-token price.

### Is Claude Fable 5.1 free?

No provider in the Sovyron catalog lists a free tier for Claude Fable 5.1.

### Is Claude Fable 5.1 included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Claude Fable 5.1?

Claude Fable 5.1 supports a 1.0M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/claude-fable-5-1/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.3 Codex API prices

GPT-5.3 Codex (gpt-codex) — 400k context, 128k max output.
29 metered per-token offers from 29 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $1.4 | $11.2 | $0.144 | 400k |
| Poe | $1.6 | $13 | $0.16 | 400k |
| Abacus | $1.75 | $14 | $0.18 | 400k |
| AIHubMix | $1.75 | $14 | $0.175 | 400k |
| Azure | $1.75 | $14 | $0.175 | 400k |
| Azure Cognitive Services | $1.75 | $14 | $0.175 | 400k |
| DigitalOcean | $1.75 | $14 | $0.175 | 400k |
| Eden AI | $1.75 | $14 | $0.175 | 400k |
| FastRouter | $1.75 | $14 | — | 400k |
| FreeModel | $1.75 | $14 | $0.175 | 400k |
| FrogBot | $1.75 | $14 | $0.175 | 400k |
| Impossibl | $1.75 | $14 | $0.175 | 400k |
| Kilo Gateway | $1.75 | $14 | $0.175 | 400k |
| DevPass (LLM Gateway) | $1.75 | $14 | $0.175 | 400k |
| LLM Gateway | $1.75 | $14 | $0.175 | 400k |
| LLM Gateway | $1.75 | $14 | $0.175 | 400k |
| NanoGPT | $1.75 | $14 | $0.175 | 400k |
| Neon | $1.75 | $14 | $0.175 | 400k |
| OpenAI | $1.75 | $14 | $0.175 | 400k |
| OpenCode Zen | $1.75 | $14 | $0.175 | 400k |
| OpenRouter | $1.75 | $14 | $0.175 | 400k |
| Opper | $1.75 | $14 | $0.175 | 400k |
| OrcaRouter | $1.75 | $14 | $0.175 | 400k |
| Pioneer | $1.75 | $14 | $0.175 | 400k |
| Requesty | $1.75 | $14 | $0.175 | 400k |
| Vercel AI Gateway | $1.75 | $14 | $0.175 | 400k |
| Vivgrid | $1.75 | $14 | $0.175 | 400k |
| ZenMux | $1.75 | $14 | — | 400k |
| Venice AI | $2.19 | $17.5 | $0.219 | 400k |

## Summary

- Cheapest input: $1.4 per 1M tokens (Ofox)
- Cheapest output: $11.2 per 1M tokens (Ofox)
- First-party: $14 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-02-05
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.3 Codex API?

As of Oct 4, 2026, Ofox has the lowest GPT-5.3 Codex output price at $11.2 per 1M tokens, and Ofox has the lowest input price at $1.4 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5.3 Codex cost on OpenAI?

OpenAI charges $1.75 per 1M input tokens and $14 per 1M output tokens for GPT-5.3 Codex.

### How many providers offer GPT-5.3 Codex?

29 providers list GPT-5.3 Codex on Sovyron; 29 of them sell it at a metered per-token price.

### Is GPT-5.3 Codex free?

No provider in the Sovyron catalog lists a free tier for GPT-5.3 Codex.

### Is GPT-5.3 Codex included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of GPT-5.3 Codex?

GPT-5.3 Codex supports a 400k-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-3-codex/
Full dataset: https://sovyron.com/data/catalog.json

---

# Grok 4.6 API prices

Grok 4.6 (grok) — 524k context, 524k max output.
32 metered per-token offers from 31 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| 302.AI | $2 | $6 | — | 500k |
| Abacus | $2 | $6 | $0.5 | 500k |
| AIHubMix | $2 | $6 | $0.5 | 500k |
| Amazon Bedrock (global) | $2 | $6 | $0.5 | 500k |
| Cloudflare AI Gateway | $2 | $6 | $0.5 | 500k |
| CrossModel | $2 | $6 | $0.5 | 500k |
| Eden AI | $2 | $6 | $0.5 | 500k |
| Vertex | $2 | $6 | $0.5 | 524k |
| Kilo Gateway | $2 | $6 | $0.5 | 500k |
| DevPass (LLM Gateway) | $2 | $6 | $0.5 | 500k |
| LLM Gateway | $2 | $6 | $0.5 | 500k |
| LLM Gateway | $2 | $6 | $0.5 | 500k |
| LLM Gateway | $2 | $6 | $0.5 | 500k |
| Merge Gateway | $2 | $6 | $0.5 | 500k |
| NanoGPT | $2 | $6 | $0.5 | 500k |
| Neon | $2 | $6 | $0.5 | 500k |
| OCI Generative AI | $2 | $6 | $0.5 | 500k |
| Ofox | $2 | $6 | $0.5 | 500k |
| OpenCode Zen | $2 | $6 | $0.5 | 500k |
| OpenCode Go | $2 | $6 | $0.5 | 500k |
| OpenRouter | $2 | $6 | $0.5 | 500k |
| Opper | $2 | $6 | $0.5 | 500k |
| OrcaRouter | $2 | $6 | $0.5 | 500k |
| Perplexity Agent | $2 | $6 | $0.5 | 500k |
| Requesty | $2 | $6 | $0.5 | 500k |
| Tempr Gateway | $2 | $6 | $0.5 | 500k |
| Vercel AI Gateway | $2 | $6 | $0.5 | 500k |
| xAI | $2 | $6 | $0.5 | 500k |
| ZenMux | $2 | $6 | $0.5 | 500k |
| Amazon Bedrock (us) | $2.2 | $6.6 | $0.55 | 500k |
| Amazon Bedrock | $2.2 | $6.6 | $0.55 | 500k |
| Venice AI | $2.27 | $6.8 | $0.57 | 500k |

## Summary

- Cheapest input: $2 per 1M tokens (302.AI)
- Cheapest output: $6 per 1M tokens (302.AI)
- First-party: $6 per 1M output tokens (xAI)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-08-12
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Grok 4.6 API?

As of Oct 4, 2026, 302.AI has the lowest Grok 4.6 output price at $6 per 1M tokens, and 302.AI has the lowest input price at $2 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Grok 4.6 cost on xAI?

xAI charges $2 per 1M input tokens and $6 per 1M output tokens for Grok 4.6.

### How many providers offer Grok 4.6?

31 providers list Grok 4.6 on Sovyron; 32 of them sell it at a metered per-token price.

### Is Grok 4.6 free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is Grok 4.6 included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Grok 4.6?

Grok 4.6 supports a 524k-token context window and up to 524k output tokens.

HTML page: https://sovyron.com/models/grok-4-6/
Full dataset: https://sovyron.com/data/catalog.json

---

# Qwen3.8 Max API prices

Qwen3.8 Max (qwen) — 1.0M context, 1.0M max output.
32 metered per-token offers from 33 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| AIHubMix | $0.338 | $1.014 | $0.0676 | 1.0M |
| Vancine | $1.6 | $4.8 | $0.2 | 1.0M |
| Deep Infra | $1.65 | $4.951 | $0.206 | 256k |
| AIHubMix | $1.69 | $5.07 | $0.169 | 991k |
| Ofox | $1.71 | $5.14 | $0.17 | 1.0M |
| Alibaba (China) | $1.7774 | $5.3323 | $0.2222 | 1.0M |
| SCX.ai | $1.815 | $5.4461 | $0.17 | 1.0M |
| CrossModel | $1.88 | $5.63 | $0.23 | 1.0M |
| Abacus | $2 | $6 | — | 1.0M |
| Alibaba | $2 | $6 | $0.25 | 1.0M |
| Cloudflare AI Gateway | $2 | $6 | $0.25 | 1.0M |
| DigitalOcean | $2 | $6 | $0.2 | 1.0M |
| Eden AI | $2 | $6 | $0.25 | 1.0M |
| EmpirioLabs AI | $2 | $6 | $2 | 1.0M |
| Fireworks AI | $2 | $6 | $0.25 | 262k |
| GMI Cloud | $2 | $6 | $0.25 | 262k |
| Charm Hyper | $2 | $6 | $0.25 | 1.0M |
| DevPass (LLM Gateway) | $2 | $6 | $0.25 | 1.0M |
| LLM Gateway | $2 | $6 | $0.25 | 984k |
| LLM Gateway | $2 | $6 | $0.25 | 1.0M |
| LLM Gateway | $2 | $6 | $0.25 | 1.0M |
| Merge Gateway | $2 | $6 | $0.25 | 1.0M |
| Modal | $2 | $6 | $0.25 | 1.0M |
| NanoGPT | $2 | $6 | $0.25 | 991k |
| Ofox | $2 | $6 | $0.25 | 1.0M |
| OpenCode Zen | $2 | $6 | $0.25 | 262k |
| OpenCode Go | $2 | $6 | $0.25 | 1.0M |
| Opper | $2 | $6 | $0.25 | 984k |
| OrcaRouter | $2 | $6 | $0.25 | 1.0M |
| Requesty | $2 | $6 | $0.25 | 1.0M |
| 302.AI | $2.16 | $6.36 | — | 1.0M |
| Impossibl | $2.5 | $7.5 | — | 1.0M |

## Summary

- Cheapest input: $0.338 per 1M tokens (AIHubMix)
- Cheapest output: $1.014 per 1M tokens (AIHubMix)
- First-party: $6 per 1M output tokens (Alibaba)
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China), Kenari, SCNet Token Plan
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China), ClinePass, SCNet Token Plan
- Released: 2026-08-03
- Inputs: image, pdf, text, video

## FAQ

### What is the cheapest Qwen3.8 Max API?

As of Oct 4, 2026, AIHubMix has the lowest Qwen3.8 Max output price at $1.014 per 1M tokens, and AIHubMix has the lowest input price at $0.338 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Qwen3.8 Max cost on Alibaba?

Alibaba charges $2 per 1M input tokens and $6 per 1M output tokens for Qwen3.8 Max.

### How many providers offer Qwen3.8 Max?

33 providers list Qwen3.8 Max on Sovyron; 32 of them sell it at a metered per-token price.

### Is Qwen3.8 Max free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is Qwen3.8 Max included in a subscription plan?

Yes. 4 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of Qwen3.8 Max?

Qwen3.8 Max supports a 1.0M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/qwen3-8-max/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Opus 5.5 API prices

Claude Opus 5.5 (claude-opus) — 1.0M context, 128k max output.
35 metered per-token offers from 28 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| 302.AI | $4 | $20 | $0.2 | 1.0M |
| AIHubMix | $4 | $20 | $0.2 | 1.0M |
| Amazon Bedrock | $4 | $20 | $0.2 | 1.0M |
| Amazon Bedrock (global) | $4 | $20 | $0.2 | 1.0M |
| Anthropic | $4 | $20 | $0.2 | 1.0M |
| Azure | $4 | $20 | $0.2 | 1.0M |
| Azure Cognitive Services | $4 | $20 | $0.2 | 1.0M |
| Cloudflare AI Gateway | $4 | $20 | $0.2 | 1.0M |
| CrossModel | $4 | $20 | $0.2 | 1.0M |
| DigitalOcean | $4 | $20 | $0.2 | 1.0M |
| Eden AI | $4 | $20 | $0.2 | 1.0M |
| Vertex | $4 | $20 | $0.2 | 1.0M |
| Vertex (Anthropic) | $4 | $20 | $0.2 | 1.0M |
| Kilo Gateway | $4 | $20 | $0.2 | 1.0M |
| DevPass (LLM Gateway) | $4 | $20 | $0.2 | 1.0M |
| LLM Gateway | $4 | $20 | $0.2 | 1.0M |
| LLM Gateway | $4 | $20 | $0.2 | 1.0M |
| LLM Gateway | $4 | $20 | $0.2 | 1.0M |
| Merge Gateway | $4 | $20 | $0.2 | 1.0M |
| NanoGPT | $4 | $20 | $0.2 | 1.0M |
| Neon | $4 | $20 | $0.2 | 1.0M |
| Ofox | $4 | $20 | $0.2 | 1.0M |
| OpenCode Zen | $4 | $20 | $0.2 | 1.0M |
| OpenRouter | $4 | $20 | $0.2 | 1.0M |
| Requesty | $4 | $20 | $0.2 | 1.0M |
| Vercel AI Gateway | $4 | $20 | $0.2 | 1.0M |
| Vivgrid | $4 | $20 | $0.2 | 1.0M |
| ZenMux | $4 | $20 | $0.2 | 1.0M |
| Cortecs | $4.399 | $21.998 | $0.219 | 1.0M |
| Amazon Bedrock (au) | $4.4 | $22 | $0.22 | 1.0M |
| Amazon Bedrock (eu) | $4.4 | $22 | $0.22 | 1.0M |
| Amazon Bedrock (jp) | $4.4 | $22 | $0.22 | 1.0M |
| Amazon Bedrock (us) | $4.4 | $22 | $0.22 | 1.0M |
| Requesty (eu) | $4.4 | $22 | $0.22 | 1.0M |
| Venice AI | $4.8 | $24 | $0.24 | 1.0M |

## Summary

- Cheapest input: $4 per 1M tokens (302.AI)
- Cheapest output: $20 per 1M tokens (302.AI)
- First-party: $20 per 1M output tokens (Anthropic)
- Free offers: none
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-09-22
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Opus 5.5 API?

As of Oct 4, 2026, 302.AI has the lowest Claude Opus 5.5 output price at $20 per 1M tokens, and 302.AI has the lowest input price at $4 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Claude Opus 5.5 cost on Anthropic?

Anthropic charges $4 per 1M input tokens and $20 per 1M output tokens for Claude Opus 5.5.

### How many providers offer Claude Opus 5.5?

28 providers list Claude Opus 5.5 on Sovyron; 35 of them sell it at a metered per-token price.

### Is Claude Opus 5.5 free?

No provider in the Sovyron catalog lists a free tier for Claude Opus 5.5.

### Is Claude Opus 5.5 included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Claude Opus 5.5?

Claude Opus 5.5 supports a 1.0M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/claude-opus-5-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# Gemini 3.1 Flash Lite API prices

Gemini 3.1 Flash Lite (gemini-flash-lite) — 1.1M context, 66k max output.
38 metered per-token offers from 28 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Kilo Gateway | $0.125 | $0.75 | $0.0125 | 1.0M |
| Kilo Gateway | $0.125 | $0.75 | $0.0125 | 1.0M |
| 302.AI | $0.25 | $1.5 | — | 1.0M |
| 302.AI | $0.25 | $1.5 | — | 1.0M |
| Abacus | $0.25 | $1.5 | $0.025 | 1.0M |
| Abacus | $0.25 | $1.5 | $0.025 | 1.0M |
| AIHubMix | $0.25 | $1.5 | $0.025 | 1.0M |
| Databricks | $0.25 | $1.5 | $0.025 | 1.0M |
| Eden AI | $0.25 | $1.5 | $0.025 | 1.0M |
| Eden AI | $0.25 | $1.5 | $0.025 | 1.0M |
| Eden AI | $0.25 | $1.5 | $0.025 | 1.0M |
| Google | $0.25 | $1.5 | $0.025 | 1.0M |
| Vertex | $0.25 | $1.5 | $0.025 | 1.0M |
| Impossibl | $0.25 | $1.5 | $0.025 | 1.0M |
| DevPass (LLM Gateway) | $0.25 | $1.5 | $0.025 | 1.0M |
| LLM Gateway | $0.25 | $1.5 | $0.025 | 1.0M |
| LLM Gateway | $0.25 | $1.5 | $0.025 | 1.0M |
| Merge Gateway | $0.25 | $1.5 | $0.025 | 1.0M |
| Merge Gateway | $0.25 | $1.5 | $0.025 | 1.0M |
| NanoGPT | $0.25 | $1.5 | $0.025 | 1.0M |
| NEAR AI Cloud | $0.25 | $1.5 | $0.025 | 1.0M |
| Neon | $0.25 | $1.5 | $0.025 | 1.0M |
| Ofox | $0.25 | $1.5 | $0.025 | 1.0M |
| OpenRouter | $0.25 | $1.5 | $0.025 | 1.0M |
| OpenRouter | $0.25 | $1.5 | $0.025 | 1.0M |
| OrcaRouter | $0.25 | $1.5 | $0.025 | 1.0M |
| OrcaRouter | $0.25 | $1.5 | $0.025 | 1.0M |
| Pioneer | $0.25 | $1.5 | $0.03 | 1.0M |
| Poe | $0.25 | $1.5 | — | 1.0M |
| Requesty | $0.25 | $1.5 | $0.025 | 1.0M |
| SAP AI Core | $0.25 | $1.5 | $0.025 | 1.0M |
| Tempr Gateway | $0.25 | $1.5 | $0.025 | 1.0M |
| Vercel AI Gateway | $0.25 | $1.5 | $0.03 | 1.0M |
| Vivgrid | $0.25 | $1.5 | $0.025 | 1.0M |
| ZenMux | $0.25 | $1.5 | $0.025 | 1.0M |
| ZenMux | $0.25 | $1.5 | — | 1.1M |
| Cortecs | $0.272 | $1.631 | $0.025 | 1.0M |
| Requesty (eu) | $0.275 | $1.65 | $0.0275 | 1.0M |

## Summary

- Cheapest input: $0.125 per 1M tokens (Kilo Gateway)
- Cheapest output: $0.75 per 1M tokens (Kilo Gateway)
- First-party: $1.5 per 1M output tokens (Google)
- Free offers: Kenari
- Subscription plans (not per-token): none
- Released: 2026-05-07
- Inputs: audio, image, pdf, text, video

## FAQ

### What is the cheapest Gemini 3.1 Flash Lite API?

As of Oct 4, 2026, Kilo Gateway has the lowest Gemini 3.1 Flash Lite output price at $0.75 per 1M tokens, and Kilo Gateway has the lowest input price at $0.125 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Gemini 3.1 Flash Lite cost on Google?

Google charges $0.25 per 1M input tokens and $1.5 per 1M output tokens for Gemini 3.1 Flash Lite.

### How many providers offer Gemini 3.1 Flash Lite?

28 providers list Gemini 3.1 Flash Lite on Sovyron; 38 of them sell it at a metered per-token price.

### Is Gemini 3.1 Flash Lite free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### What is the context window of Gemini 3.1 Flash Lite?

Gemini 3.1 Flash Lite supports a 1.1M-token context window and up to 66k output tokens.

HTML page: https://sovyron.com/models/gemini-3-1-flash-lite/
Full dataset: https://sovyron.com/data/catalog.json

---

# Qwen3.5 397B-A17B API prices

Qwen3.5 397B-A17B (qwen) — 262k context, 262k max output.
28 metered per-token offers from 28 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| AIHubMix | $0.1644 | $0.9864 | — | 262k |
| Alibaba (China) | $0.172 | $1.032 | — | 262k |
| EmpirioLabs AI | $0.172 | $1.032 | $0.172 | 256k |
| Merge Gateway | $0.172 | $1.032 | $0.0344 | 131k |
| OrcaRouter | $0.172 | $1.032 | — | 262k |
| CrofAI | $0.35 | $1.75 | $0.07 | 262k |
| Kilo Gateway | $0.39 | $2.34 | — | 262k |
| SiliconFlow | $0.39 | $2.34 | — | 262k |
| TokenGo | $0.4 | $2.65 | $0.2 | 262k |
| Ofox | $0.55 | $3.5 | $0.55 | 256k |
| Ofox | $0.55 | $3.5 | $0.55 | 256k |
| OpenRouter | $0.55 | $3.5 | $0.225 | 262k |
| Alibaba | $0.6 | $3.6 | — | 262k |
| Cloudflare AI Gateway | $0.6 | $3.6 | — | 262k |
| Hugging Face | $0.6 | $3.6 | — | 262k |
| Jalapeno Cloud | $0.6 | $3.6 | — | 262k |
| DevPass (LLM Gateway) | $0.6 | $3.6 | — | 262k |
| LLM Gateway | $0.6 | $3.6 | — | 262k |
| LLM Gateway | $0.6 | $3.6 | — | 262k |
| LLMTR | $0.6 | $3.6 | — | 256k |
| Mixlayer | $0.6 | $3.6 | — | 262k |
| NanoGPT | $0.6 | $3.6 | $0.3 | 258k |
| Nebius Token Factory | $0.6 | $3.6 | $0.06 | 262k |
| NovitaAI | $0.6 | $3.6 | — | 262k |
| Scaleway | $0.6 | $3.6 | — | 256k |
| Cortecs | $0.668 | $4.01 | — | 262k |
| OVHcloud AI Endpoints | $0.71 | $4.25 | — | 262k |
| GreenPT | $0.798 | $4.959 | — | 262k |

## Summary

- Cheapest input: $0.1644 per 1M tokens (AIHubMix)
- Cheapest output: $0.9864 per 1M tokens (AIHubMix)
- First-party: $3.6 per 1M output tokens (Alibaba)
- Free offers: UnoRouter
- Subscription plans (not per-token): none
- Released: 2026-02-15
- Inputs: audio, image, text, video

## FAQ

### What is the cheapest Qwen3.5 397B-A17B API?

As of Oct 4, 2026, AIHubMix has the lowest Qwen3.5 397B-A17B output price at $0.9864 per 1M tokens, and AIHubMix has the lowest input price at $0.1644 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Qwen3.5 397B-A17B cost on Alibaba?

Alibaba charges $0.6 per 1M input tokens and $3.6 per 1M output tokens for Qwen3.5 397B-A17B.

### How many providers offer Qwen3.5 397B-A17B?

28 providers list Qwen3.5 397B-A17B on Sovyron; 28 of them sell it at a metered per-token price.

### Is Qwen3.5 397B-A17B free?

1 provider(s) list a free-tier offer: UnoRouter. Free tiers usually have rate limits.

### What is the context window of Qwen3.5 397B-A17B?

Qwen3.5 397B-A17B supports a 262k-token context window and up to 262k output tokens.

HTML page: https://sovyron.com/models/qwen3-5-397b-a17b/
Full dataset: https://sovyron.com/data/catalog.json

---

# Qwen3.6 35B-A3B API prices

Qwen3.6 35B-A3B (qwen) — 262k context, 262k max output.
27 metered per-token offers from 29 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| engy | $0.045 | $0.3 | $0.015 | 208k |
| EmpirioLabs AI | $0.07 | $0.42 | $0.035 | 131k |
| SaladCloud AI Gateway | $0.09 | $0.6 | — | 262k |
| AKI.IO | $0.15 | $0.5 | — | 256k |
| Zenifra | $0.19 | $0.48 | — | 262k |
| Cortecs | $0.167 | $0.557 | — | 262k |
| NanoGPT | $0.112 | $0.8 | $0.056 | 262k |
| Deep Infra | $0.1 | $0.95 | $0.1 | 262k |
| Hugging Face | $0.15 | $0.95 | — | 262k |
| Pioneer | $0.14 | $1 | $0.028 | 262k |
| Kilo Gateway | $0.15 | $1 | $0.05 | 262k |
| OpenRouter | $0.15 | $1 | $0.05 | 262k |
| CoreWeave | $0.25 | $1.25 | $0.25 | 262k |
| SiliconFlow | $0.2 | $1.6 | — | 262k |
| Alibaba | $0.248 | $1.485 | — | 262k |
| DevPass (LLM Gateway) | $0.248 | $1.485 | — | 262k |
| LLM Gateway | $0.248 | $1.485 | — | 262k |
| Merge Gateway | $0.248 | $1.485 | $0.0496 | 262k |
| Opper | $0.248 | $1.485 | — | 262k |
| OrcaRouter | $0.248 | $1.485 | — | 262k |
| Scaleway | $0.25 | $1.5 | — | 128k |
| AIHubMix | $0.254 | $1.524 | — | 262k |
| evroc | $0.345 | $1.38 | — | 262k |
| 302.AI | $0.283 | $1.705 | — | 262k |
| GreenPT | $0.342 | $2.052 | — | 262k |
| LLM Gateway | $0.375 | $2.25 | — | 262k |
| LLMTR | $5 | $10 | — | 16k |

## Summary

- Cheapest input: $0.045 per 1M tokens (engy)
- Cheapest output: $0.3 per 1M tokens (engy)
- First-party: $1.485 per 1M output tokens (Alibaba)
- Free offers: NaN, QVAC, Umans AI Coding Plan
- Subscription plans (not per-token): Umans AI Coding Plan
- Released: 2026-04-17
- Inputs: audio, image, text, video

## FAQ

### What is the cheapest Qwen3.6 35B-A3B API?

As of Oct 4, 2026, engy has the lowest Qwen3.6 35B-A3B output price at $0.3 per 1M tokens, and engy has the lowest input price at $0.045 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Qwen3.6 35B-A3B cost on Alibaba?

Alibaba charges $0.248 per 1M input tokens and $1.485 per 1M output tokens for Qwen3.6 35B-A3B.

### How many providers offer Qwen3.6 35B-A3B?

29 providers list Qwen3.6 35B-A3B on Sovyron; 27 of them sell it at a metered per-token price.

### Is Qwen3.6 35B-A3B free?

2 provider(s) list a free-tier offer: NaN, QVAC. Free tiers usually have rate limits.

### What is the context window of Qwen3.6 35B-A3B?

Qwen3.6 35B-A3B supports a 262k-token context window and up to 262k output tokens.

HTML page: https://sovyron.com/models/qwen3-6-35b-a3b/
Full dataset: https://sovyron.com/data/catalog.json

---

# Qwen3.7 Max API prices

Qwen3.7 Max (qwen) — 1.1M context, 500k max output.
28 metered per-token offers from 29 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Merge Gateway | $0.825 | $2.4755 | $0.165 | 1.0M |
| Cloudflare AI Gateway | $1.25 | $3.75 | $0.25 | 1.0M |
| DevPass (LLM Gateway) | $1.25 | $3.75 | $0.25 | 1.0M |
| LLM Gateway | $1.25 | $3.75 | $0.25 | 1.0M |
| NovitaAI | $1.25 | $3.75 | $0.25 | 1.0M |
| OrcaRouter | $1.25 | $3.75 | $0.25 | 1.0M |
| Pioneer | $1.25 | $3.75 | $0.25 | 991k |
| Together AI | $1.25 | $3.75 | $0.125 | 1.0M |
| Kilo Gateway | $1.475 | $4.425 | $0.295 | 1.0M |
| OpenRouter | $1.475 | $4.425 | $0.295 | 1.0M |
| AIHubMix | $1.69 | $5.07 | $0.169 | 991k |
| Ofox | $1.71 | $5.14 | $0.17 | 1.1M |
| 302.AI | $1.8 | $5.3 | — | 1.0M |
| CrossModel | $1.88 | $5.63 | $0.375 | 1.0M |
| Abacus | $2.5 | $7.5 | — | 1.0M |
| Alibaba | $2.5 | $7.5 | $0.5 | 1.0M |
| Alibaba (China) | $2.5 | $7.5 | $0.5 | 1.0M |
| Deep Infra | $2.5 | $7.5 | $0.5 | 256k |
| EmpirioLabs AI | $2.5 | $7.5 | $2.5 | 1.0M |
| GMI Cloud | $2.5 | $7.5 | $0.25 | 1.0M |
| Charm Hyper | $2.5 | $7.5 | $0.5 | 1.0M |
| Impossibl | $2.5 | $7.5 | $0.5 | 1.0M |
| LLM Gateway | $2.5 | $7.5 | $0.5 | 984k |
| NanoGPT | $2.5 | $7.5 | $0.5 | 1.0M |
| Ofox | $2.5 | $7.5 | $0.5 | 1.0M |
| Requesty | $2.5 | $7.5 | $0.25 | 1.0M |
| ZenMux | $2.5 | $7.5 | $0.5 | 1.0M |
| Modelis | $3 | $9 | — | 1.0M |

## Summary

- Cheapest input: $0.825 per 1M tokens (Merge Gateway)
- Cheapest output: $2.4755 per 1M tokens (Merge Gateway)
- First-party: $7.5 per 1M output tokens (Alibaba)
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China)
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China), ClinePass
- Released: 2026-05-21
- Inputs: text

## FAQ

### What is the cheapest Qwen3.7 Max API?

As of Oct 4, 2026, Merge Gateway has the lowest Qwen3.7 Max output price at $2.4755 per 1M tokens, and Merge Gateway has the lowest input price at $0.825 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Qwen3.7 Max cost on Alibaba?

Alibaba charges $2.5 per 1M input tokens and $7.5 per 1M output tokens for Qwen3.7 Max.

### How many providers offer Qwen3.7 Max?

29 providers list Qwen3.7 Max on Sovyron; 28 of them sell it at a metered per-token price.

### Is Qwen3.7 Max free?

No provider in the Sovyron catalog lists a free tier for Qwen3.7 Max.

### Is Qwen3.7 Max included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of Qwen3.7 Max?

Qwen3.7 Max supports a 1.1M-token context window and up to 500k output tokens.

HTML page: https://sovyron.com/models/qwen3-7-max/
Full dataset: https://sovyron.com/data/catalog.json

---

# GLM-4.6 API prices

GLM-4.6 (glm) — 205k context, 200k max output.
26 metered per-token offers from 29 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| AIHubMix | $0.274 | $1.0959 | $0.0548 | 205k |
| 302.AI | $0.286 | $1.142 | — | 205k |
| ZenMux | $0.2911 | $1.1645 | $0.0582 | 200k |
| NanoGPT | $0.35 | $1.4 | $0.175 | 200k |
| Helicone | $0.45 | $1.5 | — | 205k |
| IO.NET | $0.4 | $1.75 | $0.2 | 200k |
| Kilo Gateway | $0.43 | $1.75 | $0.08 | 198k |
| OpenRouter | $0.43 | $1.75 | $0.08 | 205k |
| Venice AI | $0.43 | $1.75 | $0.08 | 198k |
| Meganova | $0.45 | $1.9 | — | 203k |
| Deep Infra | $0.5 | $2 | $0.1 | 203k |
| Hugging Face | $0.55 | $2.2 | — | 205k |
| DevPass (LLM Gateway) | $0.55 | $2.2 | $0.11 | 205k |
| LLM Gateway | $0.55 | $2.2 | $0.11 | 205k |
| NovitaAI | $0.55 | $2.2 | $0.11 | 205k |
| Abacus | $0.6 | $2.2 | — | 203k |
| Eden AI | $0.6 | $2.2 | $0.11 | 203k |
| Impossibl | $0.6 | $2.2 | $0.11 | 205k |
| LLM Gateway | $0.6 | $2.2 | $0.11 | 200k |
| Merge Gateway | $0.6 | $2.2 | $0.11 | 200k |
| Ofox | $0.6 | $2.2 | $0.11 | 205k |
| OrcaRouter | $0.6 | $2.2 | $0.11 | 205k |
| Tempr Gateway | $0.6 | $2.2 | $0.11 | 205k |
| Vercel AI Gateway | $0.6 | $2.2 | $0.11 | 200k |
| Z.AI | $0.6 | $2.2 | $0.11 | 205k |
| Zhipu AI | $0.6 | $2.2 | $0.11 | 205k |

## Summary

- Cheapest input: $0.274 per 1M tokens (AIHubMix)
- Cheapest output: $1.0959 per 1M tokens (AIHubMix)
- First-party: $2.2 per 1M output tokens (Z.AI)
- Free offers: iFlow, ModelScope
- Subscription plans (not per-token): none
- Released: 2025-09-30
- Inputs: text

## FAQ

### What is the cheapest GLM-4.6 API?

As of Oct 4, 2026, AIHubMix has the lowest GLM-4.6 output price at $1.0959 per 1M tokens, and AIHubMix has the lowest input price at $0.274 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GLM-4.6 cost on Z.AI?

Z.AI charges $0.6 per 1M input tokens and $2.2 per 1M output tokens for GLM-4.6.

### How many providers offer GLM-4.6?

29 providers list GLM-4.6 on Sovyron; 26 of them sell it at a metered per-token price.

### Is GLM-4.6 free?

2 provider(s) list a free-tier offer: ModelScope, iFlow. Free tiers usually have rate limits.

### What is the context window of GLM-4.6?

GLM-4.6 supports a 205k-token context window and up to 200k output tokens.

HTML page: https://sovyron.com/models/glm-4-6/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-6 Astra API prices

GPT-6 Astra (gpt-astra) — 1.1M context, 1.1M max output.
28 metered per-token offers from 26 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $8 | $40 | $0.8 | 1.1M |
| 302.AI | $10 | $50 | — | 1.1M |
| AIHubMix | $10 | $50 | $1 | 1.1M |
| Amazon Bedrock (global) | $10 | $50 | $1 | 1.1M |
| Azure | $10 | $50 | $1 | 1.1M |
| Azure Cognitive Services | $10 | $50 | $1 | 1.1M |
| Cloudflare AI Gateway | $10 | $50 | $1 | 1.1M |
| CrossModel | $10 | $50 | $1 | 1.1M |
| DigitalOcean | $10 | $50 | $1 | 1.1M |
| Eden AI | $10 | $50 | $1 | 1.1M |
| Kilo Gateway | $10 | $50 | $1 | 1.1M |
| DevPass (LLM Gateway) | $10 | $50 | $1 | 1.1M |
| LLM Gateway | $10 | $50 | $1 | 1.1M |
| LLM Gateway | $10 | $50 | $1 | 1.1M |
| Merge Gateway | $10 | $50 | $1 | 1.1M |
| NanoGPT | $10 | $50 | $1 | 1.1M |
| Neon | $10 | $50 | $1 | 1.1M |
| OpenAI | $10 | $50 | $1 | 1.1M |
| OpenCode Zen | $10 | $50 | $1 | 1.1M |
| OpenRouter | $10 | $50 | $1 | 1.1M |
| Opper | $10 | $50 | $1 | 1.1M |
| Requesty | $10 | $50 | $1 | 1.1M |
| Venice AI | $10 | $50 | $1 | 1.1M |
| Vercel AI Gateway | $10 | $50 | $1 | 1.1M |
| Vivgrid | $10 | $50 | $1 | 1.1M |
| ZenMux | $10 | $50 | $1 | 1.1M |
| Amazon Bedrock | $11 | $55 | $1.1 | 1.1M |
| Amazon Bedrock (us) | $11 | $55 | $1.1 | 1.1M |

## Summary

- Cheapest input: $8 per 1M tokens (Ofox)
- Cheapest output: $40 per 1M tokens (Ofox)
- First-party: $50 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-09-04
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-6 Astra API?

As of Oct 4, 2026, Ofox has the lowest GPT-6 Astra output price at $40 per 1M tokens, and Ofox has the lowest input price at $8 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-6 Astra cost on OpenAI?

OpenAI charges $10 per 1M input tokens and $50 per 1M output tokens for GPT-6 Astra.

### How many providers offer GPT-6 Astra?

26 providers list GPT-6 Astra on Sovyron; 28 of them sell it at a metered per-token price.

### Is GPT-6 Astra free?

No provider in the Sovyron catalog lists a free tier for GPT-6 Astra.

### Is GPT-6 Astra included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of GPT-6 Astra?

GPT-6 Astra supports a 1.1M-token context window and up to 1.1M output tokens.

HTML page: https://sovyron.com/models/gpt-6-astra/
Full dataset: https://sovyron.com/data/catalog.json

---

# Gemini 3.5 Flash Lite API prices

Gemini 3.5 Flash Lite (gemini-flash-lite) — 1.0M context, 66k max output.
28 metered per-token offers from 26 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Kilo Gateway | $0.15 | $1.25 | $0.015 | 1.0M |
| AIHubMix | $0.3 | $2.5 | $0.03 | 1.0M |
| 302.AI | $0.3 | $2.5 | — | 1.0M |
| Abacus | $0.3 | $2.5 | $0.03 | 1.0M |
| CrossModel | $0.3 | $2.5 | $0.03 | 1.0M |
| Eden AI | $0.3 | $2.5 | $0.03 | 1.0M |
| Eden AI | $0.3 | $2.5 | $0.03 | 1.0M |
| Google | $0.3 | $2.5 | $0.03 | 1.0M |
| Vertex | $0.3 | $2.5 | $0.03 | 1.0M |
| Impossibl | $0.3 | $2.5 | $0.03 | 1.0M |
| DevPass (LLM Gateway) | $0.3 | $2.5 | $0.03 | 1.0M |
| LLM Gateway | $0.3 | $2.5 | $0.03 | 1.0M |
| LLM Gateway | $0.3 | $2.5 | $0.03 | 1.0M |
| Merge Gateway | $0.3 | $2.5 | $0.03 | 1.0M |
| NanoGPT | $0.3 | $2.5 | $0.03 | 1.0M |
| Neon | $0.3 | $2.5 | $0.03 | 1.0M |
| Ofox | $0.3 | $2.5 | $0.03 | 1.0M |
| OpenCode Zen | $0.3 | $2.5 | $0.03 | 1.0M |
| OpenRouter | $0.3 | $2.5 | $0.03 | 1.0M |
| Opper | $0.3 | $2.5 | $0.03 | 1.0M |
| OrcaRouter | $0.3 | $2.5 | $0.03 | 1.0M |
| Pioneer | $0.3 | $2.5 | $0.03 | 1.0M |
| Requesty | $0.3 | $2.5 | $0.03 | 1.0M |
| Tempr Gateway | $0.3 | $2.5 | $0.03 | 1.0M |
| Vercel AI Gateway | $0.3 | $2.5 | $0.03 | 1.0M |
| Cortecs | $0.33 | $2.749 | $0.033 | 1.0M |
| Requesty (eu) | $0.33 | $2.75 | $0.033 | 1.0M |
| Venice AI | $0.375 | $3.125 | $0.0375 | 1.0M |

## Summary

- Cheapest input: $0.15 per 1M tokens (Kilo Gateway)
- Cheapest output: $1.25 per 1M tokens (Kilo Gateway)
- First-party: $2.5 per 1M output tokens (Google)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-07-21
- Inputs: audio, image, pdf, text, video

## FAQ

### What is the cheapest Gemini 3.5 Flash Lite API?

As of Oct 4, 2026, Kilo Gateway has the lowest Gemini 3.5 Flash Lite output price at $1.25 per 1M tokens, and Kilo Gateway has the lowest input price at $0.15 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Gemini 3.5 Flash Lite cost on Google?

Google charges $0.3 per 1M input tokens and $2.5 per 1M output tokens for Gemini 3.5 Flash Lite.

### How many providers offer Gemini 3.5 Flash Lite?

26 providers list Gemini 3.5 Flash Lite on Sovyron; 28 of them sell it at a metered per-token price.

### Is Gemini 3.5 Flash Lite free?

No provider in the Sovyron catalog lists a free tier for Gemini 3.5 Flash Lite.

### What is the context window of Gemini 3.5 Flash Lite?

Gemini 3.5 Flash Lite supports a 1.0M-token context window and up to 66k output tokens.

HTML page: https://sovyron.com/models/gemini-3-5-flash-lite/
Full dataset: https://sovyron.com/data/catalog.json

---

# Grok 4.5 API prices

Grok 4.5 (grok) — 1.0M context, 1.0M max output.
25 metered per-token offers from 27 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| 302.AI | $2 | $6 | — | 500k |
| Abacus | $2 | $6 | — | 500k |
| AIHubMix | $2 | $6 | $0.5 | 1.0M |
| Cloudflare AI Gateway | $2 | $6 | $0.3 | 500k |
| CrossModel | $2 | $6 | $0.3 | 500k |
| DaoXE | $2 | $6 | $0.5 | 500k |
| Eden AI | $2 | $6 | $0.3 | 500k |
| Impossibl | $2 | $6 | $0.3 | 500k |
| Kilo Gateway | $2 | $6 | $0.3 | 500k |
| DevPass (LLM Gateway) | $2 | $6 | $0.3 | 500k |
| LLM Gateway | $2 | $6 | $0.3 | 500k |
| Merge Gateway | $2 | $6 | $0.5 | 500k |
| NanoGPT | $2 | $6 | $0.5 | 500k |
| Ofox | $2 | $6 | $0.3 | 500k |
| OpenCode Zen | $2 | $6 | $0.3 | 500k |
| OpenRouter | $2 | $6 | $0.3 | 500k |
| Opper | $2 | $6 | $0.5 | 500k |
| OrcaRouter | $2 | $6 | $0.5 | 500k |
| Pioneer | $2 | $6 | $0.5 | 500k |
| Requesty | $2 | $6 | $0.5 | 500k |
| Tempr Gateway | $2 | $6 | $0.3 | 500k |
| Vercel AI Gateway | $2 | $6 | $0.3 | 500k |
| xAI | $2 | $6 | $0.3 | 500k |
| ZenMux | $2 | $6 | $0.5 | 500k |
| Venice AI | $2.27 | $6.8 | $0.34 | 500k |

## Summary

- Cheapest input: $2 per 1M tokens (302.AI)
- Cheapest output: $6 per 1M tokens (302.AI)
- First-party: $6 per 1M output tokens (xAI)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-07-08
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Grok 4.5 API?

As of Oct 4, 2026, 302.AI has the lowest Grok 4.5 output price at $6 per 1M tokens, and 302.AI has the lowest input price at $2 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Grok 4.5 cost on xAI?

xAI charges $2 per 1M input tokens and $6 per 1M output tokens for Grok 4.5.

### How many providers offer Grok 4.5?

27 providers list Grok 4.5 on Sovyron; 25 of them sell it at a metered per-token price.

### Is Grok 4.5 free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is Grok 4.5 included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Grok 4.5?

Grok 4.5 supports a 1.0M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/grok-4-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-4.1 API prices

GPT-4.1 (gpt) — 1.0M context, 33k max output.
25 metered per-token offers from 27 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $1.6 | $6.4 | $0.4 | 1.0M |
| Poe | $1.8 | $7.2 | $0.45 | 1.0M |
| 302.AI | $2 | $8 | — | 1.0M |
| Abacus | $2 | $8 | $0.5 | 1.0M |
| Cloudflare AI Gateway | $2 | $8 | $0.5 | 1.0M |
| DigitalOcean | $2 | $8 | $0.5 | 1.0M |
| Eden AI | $2 | $8 | $0.5 | 1.0M |
| FastRouter | $2 | $8 | $0.5 | 1.0M |
| Helicone | $2 | $8 | $0.5 | 1.0M |
| Impossibl | $2 | $8 | $0.5 | 1.0M |
| Kilo Gateway | $2 | $8 | $0.5 | 1.0M |
| DevPass (LLM Gateway) | $2 | $8 | $0.5 | 1.0M |
| LLM Gateway | $2 | $8 | $0.5 | 1.0M |
| LLM Gateway | $2 | $8 | $0.5 | 1.0M |
| Merge Gateway | $2 | $8 | $0.5 | 1.0M |
| NanoGPT | $2 | $8 | $0.5 | 1.0M |
| NEAR AI Cloud | $2 | $8 | $0.5 | 1.0M |
| OpenAI | $2 | $8 | $0.5 | 1.0M |
| OpenRouter | $2 | $8 | $0.5 | 1.0M |
| OrcaRouter | $2 | $8 | $0.5 | 1.0M |
| Pioneer | $2 | $8 | $1 | 1.0M |
| SAP AI Core | $2 | $8 | $0.32 | 1.0M |
| Vercel AI Gateway | $2 | $8 | $0.5 | 1.0M |
| Cortecs | $2.192 | $8.769 | $0.546 | 1.0M |
| Requesty (eu) | $2.2 | $8.8 | $0.55 | 1.0M |

## Summary

- Cheapest input: $1.6 per 1M tokens (Ofox)
- Cheapest output: $6.4 per 1M tokens (Ofox)
- First-party: $8 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-04-14
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-4.1 API?

As of Oct 4, 2026, Ofox has the lowest GPT-4.1 output price at $6.4 per 1M tokens, and Ofox has the lowest input price at $1.6 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-4.1 cost on OpenAI?

OpenAI charges $2 per 1M input tokens and $8 per 1M output tokens for GPT-4.1.

### How many providers offer GPT-4.1?

27 providers list GPT-4.1 on Sovyron; 25 of them sell it at a metered per-token price.

### Is GPT-4.1 free?

No provider in the Sovyron catalog lists a free tier for GPT-4.1.

### What is the context window of GPT-4.1?

GPT-4.1 supports a 1.0M-token context window and up to 33k output tokens.

HTML page: https://sovyron.com/models/gpt-4-1/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-6 Luna API prices

GPT-6 Luna (gpt-luna) — 1.1M context, 128k max output.
28 metered per-token offers from 25 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $0.08 | $0.4 | $0.008 | 1.1M |
| 302.AI | $0.1 | $0.5 | $0.01 | 1.1M |
| AIHubMix | $0.1 | $0.5 | $0.01 | 1.1M |
| Amazon Bedrock (global) | $0.1 | $0.5 | $0.01 | 1.1M |
| Azure | $0.1 | $0.5 | $0.01 | 1.1M |
| Azure Cognitive Services | $0.1 | $0.5 | $0.01 | 1.1M |
| Cloudflare AI Gateway | $0.1 | $0.5 | $0.01 | 1.1M |
| CrossModel | $0.1 | $0.5 | $0.01 | 1.1M |
| DigitalOcean | $0.1 | $0.5 | $0.01 | 1.1M |
| Eden AI | $0.1 | $0.5 | $0.01 | 1.1M |
| Kilo Gateway | $0.1 | $0.5 | $0.01 | 1.1M |
| DevPass (LLM Gateway) | $0.1 | $0.5 | $0.01 | 1.1M |
| LLM Gateway | $0.1 | $0.5 | $0.01 | 1.1M |
| LLM Gateway | $0.1 | $0.5 | $0.01 | 1.1M |
| Merge Gateway | $0.1 | $0.5 | $0.01 | 1.1M |
| NanoGPT | $0.1 | $0.5 | $0.01 | 1.1M |
| OpenAI | $0.1 | $0.5 | $0.01 | 1.1M |
| OpenCode Zen | $0.1 | $0.5 | $0.01 | 1.1M |
| OpenCode Go | $0.1 | $0.5 | $0.01 | 1.1M |
| OpenRouter | $0.1 | $0.5 | $0.01 | 1.1M |
| Requesty | $0.1 | $0.5 | $0.01 | 1.1M |
| Vercel AI Gateway | $0.1 | $0.5 | $0.01 | 1.1M |
| Vivgrid | $0.1 | $0.5 | $0.01 | 1.1M |
| Amazon Bedrock | $0.11 | $0.55 | $0.011 | 1.1M |
| Amazon Bedrock (us) | $0.11 | $0.55 | $0.011 | 1.1M |
| Cortecs | $0.12 | $0.6 | $0.012 | 1.1M |
| Requesty (eu) | $0.12 | $0.6 | $0.012 | 1.1M |
| Venice AI | $0.125 | $0.625 | $0.0125 | 1.1M |

## Summary

- Cheapest input: $0.08 per 1M tokens (Ofox)
- Cheapest output: $0.4 per 1M tokens (Ofox)
- First-party: $0.5 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-09-22
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-6 Luna API?

As of Oct 4, 2026, Ofox has the lowest GPT-6 Luna output price at $0.4 per 1M tokens, and Ofox has the lowest input price at $0.08 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-6 Luna cost on OpenAI?

OpenAI charges $0.1 per 1M input tokens and $0.5 per 1M output tokens for GPT-6 Luna.

### How many providers offer GPT-6 Luna?

25 providers list GPT-6 Luna on Sovyron; 28 of them sell it at a metered per-token price.

### Is GPT-6 Luna free?

No provider in the Sovyron catalog lists a free tier for GPT-6 Luna.

### Is GPT-6 Luna included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of GPT-6 Luna?

GPT-6 Luna supports a 1.1M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-6-luna/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-6 Sol API prices

GPT-6 Sol (gpt-sol) — 1.1M context, 128k max output.
28 metered per-token offers from 25 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $1.6 | $8 | $0.16 | 1.1M |
| 302.AI | $2 | $10 | $0.2 | 1.1M |
| AIHubMix | $2 | $10 | $0.2 | 1.1M |
| Amazon Bedrock (global) | $2 | $10 | $0.2 | 1.1M |
| Azure | $2 | $10 | $0.2 | 1.1M |
| Azure Cognitive Services | $2 | $10 | $0.2 | 1.1M |
| Cloudflare AI Gateway | $2 | $10 | $0.2 | 1.1M |
| CrossModel | $2 | $10 | $0.2 | 1.1M |
| DigitalOcean | $2 | $10 | $0.2 | 1.1M |
| Eden AI | $2 | $10 | $0.2 | 1.1M |
| Kilo Gateway | $2 | $10 | $0.2 | 1.1M |
| DevPass (LLM Gateway) | $2 | $10 | $0.2 | 1.1M |
| LLM Gateway | $2 | $10 | $0.2 | 1.1M |
| LLM Gateway | $2 | $10 | $0.2 | 1.1M |
| Merge Gateway | $2 | $10 | $0.2 | 1.1M |
| NanoGPT | $2 | $10 | $0.2 | 1.1M |
| OpenAI | $2 | $10 | $0.2 | 1.1M |
| OpenCode Zen | $2 | $10 | $0.2 | 1.1M |
| OpenRouter | $2 | $10 | $0.2 | 1.1M |
| Requesty | $2 | $10 | $0.2 | 1.1M |
| Vercel AI Gateway | $2 | $10 | $0.2 | 1.1M |
| Vivgrid | $2 | $10 | $0.2 | 1.1M |
| ZenMux | $2 | $10 | $0.2 | 1.1M |
| Amazon Bedrock | $2.2 | $11 | $0.22 | 1.1M |
| Amazon Bedrock (us) | $2.2 | $11 | $0.22 | 1.1M |
| Cortecs | $2.4 | $11.999 | $0.24 | 1.1M |
| Requesty (eu) | $2.4 | $12 | $0.24 | 1.1M |
| Venice AI | $2.5 | $12.5 | $0.25 | 1.1M |

## Summary

- Cheapest input: $1.6 per 1M tokens (Ofox)
- Cheapest output: $8 per 1M tokens (Ofox)
- First-party: $10 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-09-22
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-6 Sol API?

As of Oct 4, 2026, Ofox has the lowest GPT-6 Sol output price at $8 per 1M tokens, and Ofox has the lowest input price at $1.6 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-6 Sol cost on OpenAI?

OpenAI charges $2 per 1M input tokens and $10 per 1M output tokens for GPT-6 Sol.

### How many providers offer GPT-6 Sol?

25 providers list GPT-6 Sol on Sovyron; 28 of them sell it at a metered per-token price.

### Is GPT-6 Sol free?

No provider in the Sovyron catalog lists a free tier for GPT-6 Sol.

### Is GPT-6 Sol included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of GPT-6 Sol?

GPT-6 Sol supports a 1.1M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-6-sol/
Full dataset: https://sovyron.com/data/catalog.json

---

# Gemini 3.6 Flash API prices

Gemini 3.6 Flash (gemini-flash) — 1.0M context, 66k max output.
26 metered per-token offers from 26 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Kilo Gateway | $0.375 | $1.875 | $0.0375 | 1.0M |
| Cortecs | $0.75 | $3.75 | $0.075 | 1.0M |
| CrossModel | $0.75 | $3.75 | $0.075 | 1.0M |
| Eden AI | $0.75 | $3.75 | $0.075 | 1.0M |
| Eden AI | $0.75 | $3.75 | $0.075 | 1.0M |
| Google | $0.75 | $3.75 | $0.075 | 1.0M |
| Vertex | $0.75 | $3.75 | $0.075 | 1.0M |
| DevPass (LLM Gateway) | $0.75 | $3.75 | $0.075 | 1.0M |
| LLM Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| LLM Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| NanoGPT | $0.75 | $3.75 | $0.075 | 1.0M |
| Ofox | $0.75 | $3.75 | $0.075 | 1.0M |
| OpenRouter | $0.75 | $3.75 | $0.075 | 1.0M |
| Tempr Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| Vercel AI Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| Venice AI | $0.9375 | $4.6875 | $0.0938 | 1.0M |
| Requesty | $1.5 | $7 | $0.15 | 1.0M |
| 302.AI | $1.5 | $7.5 | — | 1.0M |
| Abacus | $1.5 | $7.5 | $0.15 | 1.0M |
| AIHubMix | $1.5 | $7.5 | $0.15 | 1.0M |
| Impossibl | $1.5 | $7.5 | $0.15 | 1.0M |
| Merge Gateway | $1.5 | $7.5 | $0.15 | 1.0M |
| Neon | $1.5 | $7.5 | $0.15 | 1.0M |
| OpenCode Zen | $1.5 | $7.5 | $0.15 | 1.0M |
| OrcaRouter | $1.5 | $7.5 | $0.15 | 1.0M |
| Pioneer | $1.5 | $7.5 | $0.15 | 1.0M |

## Summary

- Cheapest input: $0.375 per 1M tokens (Kilo Gateway)
- Cheapest output: $1.875 per 1M tokens (Kilo Gateway)
- First-party: $3.75 per 1M output tokens (Google)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-07-21
- Inputs: audio, image, pdf, text, video

## FAQ

### What is the cheapest Gemini 3.6 Flash API?

As of Oct 4, 2026, Kilo Gateway has the lowest Gemini 3.6 Flash output price at $1.875 per 1M tokens, and Kilo Gateway has the lowest input price at $0.375 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Gemini 3.6 Flash cost on Google?

Google charges $0.75 per 1M input tokens and $3.75 per 1M output tokens for Gemini 3.6 Flash.

### How many providers offer Gemini 3.6 Flash?

26 providers list Gemini 3.6 Flash on Sovyron; 26 of them sell it at a metered per-token price.

### Is Gemini 3.6 Flash free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is Gemini 3.6 Flash included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Gemini 3.6 Flash?

Gemini 3.6 Flash supports a 1.0M-token context window and up to 66k output tokens.

HTML page: https://sovyron.com/models/gemini-3-6-flash/
Full dataset: https://sovyron.com/data/catalog.json

---

# Gemma 4 31B IT API prices

Gemma 4 31B IT (gemma) — 262k context, 262k max output.
26 metered per-token offers from 32 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| DevPass (LLM Gateway) | $0.1 | $0.25 | $0.01 | 262k |
| CrofAI | $0.1 | $0.3 | $0.02 | 262k |
| Kilo Gateway | $0.09 | $0.34 | $0.05 | 262k |
| OpenRouter | $0.09 | $0.34 | $0.05 | 262k |
| Lilac | $0.11 | $0.35 | — | 262k |
| FastRouter | $0.13 | $0.38 | — | 262k |
| OrcaRouter | $0.13 | $0.38 | $0.02 | 262k |
| SiliconFlow | $0.13 | $0.4 | — | 262k |
| Abacus | $0.14 | $0.4 | — | 262k |
| Amazon Bedrock | $0.14 | $0.4 | — | 262k |
| Crusoe | $0.14 | $0.4 | $0.14 | 262k |
| Friendli | $0.14 | $0.4 | — | 262k |
| Hugging Face | $0.14 | $0.4 | — | 262k |
| LLM Gateway | $0.14 | $0.4 | — | 262k |
| Merge Gateway | $0.14 | $0.4 | — | 262k |
| Vercel AI Gateway | $0.14 | $0.4 | — | 262k |
| Deep Infra | $0.15 | $0.4 | — | 262k |
| LLM Gateway | $0.2 | $0.4 | — | 262k |
| Cortecs | $0.223 | $0.39 | — | 262k |
| ai& | $0.2 | $0.5 | $0.05 | 262k |
| Infomaniak | $0.25 | $0.5 | — | 100k |
| Pioneer | $0.5 | $0.5 | $0.5 | 33k |
| Tinfoil | $0.4 | $1 | — | 262k |
| Regolo AI | $0.46 | $2.42 | — | 100k |
| Opper | $0.4649 | $2.4406 | — | 256k |
| LLM Gateway | $0.99 | $1.49 | — | 131k |

## Summary

- Cheapest input: $0.09 per 1M tokens (Kilo Gateway)
- Cheapest output: $0.25 per 1M tokens (DevPass (LLM Gateway))
- First-party: — per 1M output tokens (Google)
- Free offers: Bothub, Kenari, Nvidia, QVAC, Requesty, UnoRouter
- Subscription plans (not per-token): none
- Released: 2026-04-02
- Inputs: image, pdf, text, video

## FAQ

### What is the cheapest Gemma 4 31B IT API?

As of Oct 4, 2026, DevPass (LLM Gateway) has the lowest Gemma 4 31B IT output price at $0.25 per 1M tokens, and Kilo Gateway has the lowest input price at $0.09 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Gemma 4 31B IT cost on Google?

Google charges — per 1M input tokens and — per 1M output tokens for Gemma 4 31B IT.

### How many providers offer Gemma 4 31B IT?

32 providers list Gemma 4 31B IT on Sovyron; 26 of them sell it at a metered per-token price.

### Is Gemma 4 31B IT free?

6 provider(s) list a free-tier offer: Bothub, Kenari, Nvidia, QVAC, Requesty, UnoRouter. Free tiers usually have rate limits.

### What is the context window of Gemma 4 31B IT?

Gemma 4 31B IT supports a 262k-token context window and up to 262k output tokens.

HTML page: https://sovyron.com/models/gemma-4-31b-it/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-4.1 mini API prices

GPT-4.1 mini (gpt-mini) — 1.0M context, 33k max output.
25 metered per-token offers from 25 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $0.32 | $1.28 | $0.08 | 1.0M |
| Poe | $0.36 | $1.4 | $0.09 | 1.0M |
| Helicone | $0.4 | $1.6 | $0.1 | 1.0M |
| Helicone | $0.4 | $1.6 | $0.1 | 1.0M |
| 302.AI | $0.4 | $1.6 | — | 1.0M |
| Abacus | $0.4 | $1.6 | $0.1 | 1.0M |
| Aixy | $0.4 | $1.6 | $0.1 | 1.0M |
| Cloudflare AI Gateway | $0.4 | $1.6 | $0.1 | 1.0M |
| Eden AI | $0.4 | $1.6 | $0.1 | 1.0M |
| Impossibl | $0.4 | $1.6 | $0.1 | 1.0M |
| Kilo Gateway | $0.4 | $1.6 | $0.1 | 1.0M |
| DevPass (LLM Gateway) | $0.4 | $1.6 | $0.1 | 1.0M |
| LLM Gateway | $0.4 | $1.6 | $0.1 | 1.0M |
| LLM Gateway | $0.4 | $1.6 | $0.1 | 1.0M |
| Merge Gateway | $0.4 | $1.6 | $0.1 | 1.0M |
| NanoGPT | $0.4 | $1.6 | $0.1 | 1.0M |
| NEAR AI Cloud | $0.4 | $1.6 | $0.1 | 1.0M |
| OpenAI | $0.4 | $1.6 | $0.1 | 1.0M |
| OpenRouter | $0.4 | $1.6 | $0.1 | 1.0M |
| OrcaRouter | $0.4 | $1.6 | $0.1 | 1.0M |
| Pioneer | $0.4 | $1.6 | $0.2 | 1.0M |
| SAP AI Core | $0.4 | $1.6 | $0.1 | 1.0M |
| Vercel AI Gateway | $0.4 | $1.6 | $0.1 | 1.0M |
| Cortecs | $0.434 | $1.704 | $0.134 | 1.0M |
| Requesty (eu) | $0.44 | $1.76 | $0.11 | 1.0M |

## Summary

- Cheapest input: $0.32 per 1M tokens (Ofox)
- Cheapest output: $1.28 per 1M tokens (Ofox)
- First-party: $1.6 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-04-14
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-4.1 mini API?

As of Oct 4, 2026, Ofox has the lowest GPT-4.1 mini output price at $1.28 per 1M tokens, and Ofox has the lowest input price at $0.32 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-4.1 mini cost on OpenAI?

OpenAI charges $0.4 per 1M input tokens and $1.6 per 1M output tokens for GPT-4.1 mini.

### How many providers offer GPT-4.1 mini?

25 providers list GPT-4.1 mini on Sovyron; 25 of them sell it at a metered per-token price.

### Is GPT-4.1 mini free?

No provider in the Sovyron catalog lists a free tier for GPT-4.1 mini.

### What is the context window of GPT-4.1 mini?

GPT-4.1 mini supports a 1.0M-token context window and up to 33k output tokens.

HTML page: https://sovyron.com/models/gpt-4-1-mini/
Full dataset: https://sovyron.com/data/catalog.json

---

# Qwen3.7 Plus API prices

Qwen3.7 Plus (qwen) — 1.1M context, 131k max output.
24 metered per-token offers from 29 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| AIHubMix | $0.282 | $1.128 | $0.0564 | 991k |
| 302.AI | $0.285 | $1.15 | — | 1.0M |
| CrossModel | $0.32 | $1.25 | $0.032 | 1.0M |
| Cloudflare AI Gateway | $0.32 | $1.28 | $0.064 | 1.0M |
| Kilo Gateway | $0.32 | $1.28 | $0.064 | 1.0M |
| OpenRouter | $0.32 | $1.28 | $0.064 | 1.0M |
| Pioneer | $0.32 | $1.28 | $0.064 | 1.0M |
| Requesty | $0.32 | $1.28 | $0.032 | 1.0M |
| OrcaRouter | $0.35 | $1.42 | $0.071 | 1.0M |
| Alibaba | $0.4 | $1.6 | $0.04 | 1.0M |
| EmpirioLabs AI | $0.4 | $1.6 | $0.4 | 1.0M |
| Impossibl | $0.4 | $1.6 | $0.08 | 1.0M |
| DevPass (LLM Gateway) | $0.4 | $1.6 | $0.08 | 984k |
| LLM Gateway | $0.4 | $1.6 | $0.08 | 984k |
| LLMTR | $0.4 | $1.6 | — | 1.0M |
| Merge Gateway | $0.4 | $1.6 | — | 1.0M |
| NanoGPT | $0.4 | $1.6 | $0.08 | 992k |
| Ofox | $0.4 | $1.6 | $0.08 | 1.0M |
| Ofox | $0.4 | $1.6 | $0.08 | 1.1M |
| OpenCode Go | $0.4 | $1.6 | $0.04 | 1.0M |
| ZenMux | $0.4 | $1.6 | $0.08 | 1.0M |
| Alibaba (China) | $0.5 | $3 | $0.05 | 1.0M |
| Modelis | $0.768 | $3.072 | — | 1.0M |
| Charm Hyper | $1.2 | $4.8 | $0.24 | 1.0M |

## Summary

- Cheapest input: $0.282 per 1M tokens (AIHubMix)
- Cheapest output: $1.128 per 1M tokens (AIHubMix)
- First-party: $1.6 per 1M output tokens (Alibaba)
- Free offers: Alibaba Coding Plan, Alibaba Coding Plan (China), Alibaba Token Plan, Alibaba Token Plan (China), Kenari
- Subscription plans (not per-token): Alibaba Coding Plan, Alibaba Coding Plan (China), Alibaba Token Plan, Alibaba Token Plan (China), ClinePass
- Released: 2026-06-02
- Inputs: image, text, video

## FAQ

### What is the cheapest Qwen3.7 Plus API?

As of Oct 4, 2026, AIHubMix has the lowest Qwen3.7 Plus output price at $1.128 per 1M tokens, and AIHubMix has the lowest input price at $0.282 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Qwen3.7 Plus cost on Alibaba?

Alibaba charges $0.4 per 1M input tokens and $1.6 per 1M output tokens for Qwen3.7 Plus.

### How many providers offer Qwen3.7 Plus?

29 providers list Qwen3.7 Plus on Sovyron; 24 of them sell it at a metered per-token price.

### Is Qwen3.7 Plus free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is Qwen3.7 Plus included in a subscription plan?

Yes. 4 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of Qwen3.7 Plus?

Qwen3.7 Plus supports a 1.1M-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/qwen3-7-plus/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Sonnet 5.5 API prices

Claude Sonnet 5.5 (claude-sonnet) — 1.0M context, 128k max output.
28 metered per-token offers from 23 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| 302.AI | $2 | $10 | $0.2 | 1.0M |
| Amazon Bedrock | $2 | $10 | $0.2 | 1.0M |
| Amazon Bedrock (global) | $2 | $10 | $0.2 | 1.0M |
| Anthropic | $2 | $10 | $0.2 | 1.0M |
| Azure | $2 | $10 | $0.2 | 1.0M |
| Azure Cognitive Services | $2 | $10 | $0.2 | 1.0M |
| CrossModel | $2 | $10 | $0.2 | 1.0M |
| DigitalOcean | $2 | $10 | $0.2 | 1.0M |
| Eden AI | $2 | $10 | $0.2 | 1.0M |
| Vertex | $2 | $10 | $0.2 | 1.0M |
| Vertex (Anthropic) | $2 | $10 | $0.2 | 1.0M |
| Kilo Gateway | $2 | $10 | $0.2 | 1.0M |
| DevPass (LLM Gateway) | $2 | $10 | $0.2 | 1.0M |
| LLM Gateway | $2 | $10 | $0.2 | 1.0M |
| LLM Gateway | $2 | $10 | $0.2 | 1.0M |
| LLM Gateway | $2 | $10 | $0.2 | 1.0M |
| Merge Gateway | $2 | $10 | $0.2 | 1.0M |
| NanoGPT | $2 | $10 | $0.2 | 1.0M |
| Ofox | $2 | $10 | $0.2 | 1.0M |
| OpenCode Zen | $2 | $10 | $0.2 | 1.0M |
| OpenRouter | $2 | $10 | $0.2 | 1.0M |
| Requesty | $2 | $10 | $0.2 | 1.0M |
| Vercel AI Gateway | $2 | $10 | $0.2 | 1.0M |
| Vivgrid | $2 | $10 | $0.2 | 1.0M |
| Amazon Bedrock (eu) | $2.2 | $11 | $0.22 | 1.0M |
| Amazon Bedrock (us) | $2.2 | $11 | $0.22 | 1.0M |
| Requesty (eu) | $2.2 | $11 | $0.22 | 1.0M |
| Venice AI | $2.5 | $12.5 | $0.25 | 1.0M |

## Summary

- Cheapest input: $2 per 1M tokens (302.AI)
- Cheapest output: $10 per 1M tokens (302.AI)
- First-party: $10 per 1M output tokens (Anthropic)
- Free offers: none
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-09-28
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Sonnet 5.5 API?

As of Oct 4, 2026, 302.AI has the lowest Claude Sonnet 5.5 output price at $10 per 1M tokens, and 302.AI has the lowest input price at $2 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Claude Sonnet 5.5 cost on Anthropic?

Anthropic charges $2 per 1M input tokens and $10 per 1M output tokens for Claude Sonnet 5.5.

### How many providers offer Claude Sonnet 5.5?

23 providers list Claude Sonnet 5.5 on Sovyron; 28 of them sell it at a metered per-token price.

### Is Claude Sonnet 5.5 free?

No provider in the Sovyron catalog lists a free tier for Claude Sonnet 5.5.

### Is Claude Sonnet 5.5 included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Claude Sonnet 5.5?

Claude Sonnet 5.5 supports a 1.0M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/claude-sonnet-5-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-4o mini API prices

GPT-4o mini (gpt-mini) — 128k context, 16k max output.
24 metered per-token offers from 22 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Cloudflare AI Gateway | $0.075 | $0.3 | $0.0375 | 128k |
| Ofox | $0.12 | $0.48 | $0.06 | 128k |
| Poe | $0.14 | $0.54 | $0.068 | 124k |
| Abacus | $0.15 | $0.6 | — | 128k |
| CrossModel | $0.15 | $0.6 | $0.075 | 128k |
| DigitalOcean | $0.15 | $0.6 | $0.075 | 128k |
| Eden AI | $0.15 | $0.6 | $0.075 | 128k |
| Helicone | $0.15 | $0.6 | $0.075 | 128k |
| Impossibl | $0.15 | $0.6 | $0.075 | 128k |
| Kilo Gateway | $0.15 | $0.6 | $0.075 | 128k |
| Kilo Gateway | $0.15 | $0.6 | $0.075 | 128k |
| DevPass (LLM Gateway) | $0.15 | $0.6 | $0.075 | 128k |
| LLM Gateway | $0.15 | $0.6 | $0.075 | 128k |
| Merge Gateway | $0.15 | $0.6 | $0.075 | 128k |
| NanoGPT | $0.15 | $0.6 | $0.075 | 128k |
| OpenAI | $0.15 | $0.6 | $0.075 | 128k |
| OpenRouter | $0.15 | $0.6 | $0.075 | 128k |
| OpenRouter | $0.15 | $0.6 | $0.075 | 128k |
| OrcaRouter | $0.15 | $0.6 | $0.075 | 128k |
| Pioneer | $0.15 | $0.6 | $0.075 | 128k |
| Vercel AI Gateway | $0.15 | $0.6 | $0.075 | 128k |
| Cortecs | $0.159 | $0.638 | $0.081 | 128k |
| Requesty (eu) | $0.165 | $0.66 | $0.0825 | 128k |
| Venice AI | $0.1875 | $0.75 | $0.0938 | 128k |

## Summary

- Cheapest input: $0.075 per 1M tokens (Cloudflare AI Gateway)
- Cheapest output: $0.3 per 1M tokens (Cloudflare AI Gateway)
- First-party: $0.6 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-07-18
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-4o mini API?

As of Oct 4, 2026, Cloudflare AI Gateway has the lowest GPT-4o mini output price at $0.3 per 1M tokens, and Cloudflare AI Gateway has the lowest input price at $0.075 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-4o mini cost on OpenAI?

OpenAI charges $0.15 per 1M input tokens and $0.6 per 1M output tokens for GPT-4o mini.

### How many providers offer GPT-4o mini?

22 providers list GPT-4o mini on Sovyron; 24 of them sell it at a metered per-token price.

### Is GPT-4o mini free?

No provider in the Sovyron catalog lists a free tier for GPT-4o mini.

### What is the context window of GPT-4o mini?

GPT-4o mini supports a 128k-token context window and up to 16k output tokens.

HTML page: https://sovyron.com/models/gpt-4o-mini/
Full dataset: https://sovyron.com/data/catalog.json

---

# Gemini 2.5 Flash-Lite API prices

Gemini 2.5 Flash-Lite (gemini-flash-lite) — 1.0M context, 66k max output.
25 metered per-token offers from 25 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| LLMTR | $0.1 | $0.1 | — | 1.0M |
| Poe | $0.07 | $0.28 | — | 1.0M |
| Jiekou.AI | $0.09 | $0.36 | — | 1.0M |
| Helicone | $0.1 | $0.4 | $0.025 | 1.0M |
| AIHubMix | $0.1 | $0.4 | $0.01 | 1.0M |
| CrossModel | $0.1 | $0.4 | $0.01 | 1.0M |
| Google | $0.1 | $0.4 | $0.01 | 1.0M |
| Vertex | $0.1 | $0.4 | $0.01 | 1.0M |
| Impossibl | $0.1 | $0.4 | $0.01 | 1.0M |
| Kilo Gateway | $0.1 | $0.4 | $0.01 | 1.0M |
| DevPass (LLM Gateway) | $0.1 | $0.4 | $0.01 | 1.0M |
| LLM Gateway | $0.1 | $0.4 | $0.01 | 1.0M |
| LLM Gateway | $0.1 | $0.4 | $0.01 | 1.0M |
| Merge Gateway | $0.1 | $0.4 | $0.01 | 1.0M |
| NanoGPT | $0.1 | $0.4 | $0.01 | 1.0M |
| NanoGPT | $0.1 | $0.4 | $0.01 | 1.0M |
| NEAR AI Cloud | $0.1 | $0.4 | $0.01 | 1.0M |
| Ofox | $0.1 | $0.4 | $0.01 | 1.0M |
| OpenRouter | $0.1 | $0.4 | $0.01 | 1.0M |
| OrcaRouter | $0.1 | $0.4 | $0.01 | 1.0M |
| Requesty (eu) | $0.1 | $0.4 | $0.01 | 1.0M |
| SAP AI Core | $0.1 | $0.4 | $0.01 | 1.0M |
| Vercel AI Gateway | $0.1 | $0.4 | $0.01 | 1.0M |
| ZenMux | $0.1 | $0.4 | $0.03 | 1.0M |
| NanoGPT | $0.15 | $0.6 | $0.015 | 1.0M |

## Summary

- Cheapest input: $0.07 per 1M tokens (Poe)
- Cheapest output: $0.1 per 1M tokens (LLMTR)
- First-party: $0.4 per 1M output tokens (Google)
- Free offers: Kenari
- Subscription plans (not per-token): none
- Released: 2025-06-17
- Inputs: audio, image, pdf, text, video

## FAQ

### What is the cheapest Gemini 2.5 Flash-Lite API?

As of Oct 4, 2026, LLMTR has the lowest Gemini 2.5 Flash-Lite output price at $0.1 per 1M tokens, and Poe has the lowest input price at $0.07 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Gemini 2.5 Flash-Lite cost on Google?

Google charges $0.1 per 1M input tokens and $0.4 per 1M output tokens for Gemini 2.5 Flash-Lite.

### How many providers offer Gemini 2.5 Flash-Lite?

25 providers list Gemini 2.5 Flash-Lite on Sovyron; 25 of them sell it at a metered per-token price.

### Is Gemini 2.5 Flash-Lite free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### What is the context window of Gemini 2.5 Flash-Lite?

Gemini 2.5 Flash-Lite supports a 1.0M-token context window and up to 66k output tokens.

HTML page: https://sovyron.com/models/gemini-2-5-flash-lite/
Full dataset: https://sovyron.com/data/catalog.json

---

# Gemini 3.7 Flash API prices

Gemini 3.7 Flash (gemini-flash) — 1.0M context, 66k max output.
25 metered per-token offers from 24 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| 302.AI | $0.75 | $3.75 | — | 1.0M |
| Abacus | $0.75 | $3.75 | $0.075 | 1.0M |
| AIHubMix | $0.75 | $3.75 | $0.075 | 1.0M |
| Cortecs | $0.75 | $3.75 | $0.075 | 1.0M |
| CrossModel | $0.75 | $3.75 | $0.075 | 1.0M |
| Eden AI | $0.75 | $3.75 | $0.075 | 1.0M |
| Eden AI | $0.75 | $3.75 | $0.075 | 1.0M |
| Google | $0.75 | $3.75 | $0.075 | 1.0M |
| Vertex | $0.75 | $3.75 | $0.075 | 1.0M |
| Kilo Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| DevPass (LLM Gateway) | $0.75 | $3.75 | $0.075 | 1.0M |
| LLM Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| LLM Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| Merge Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| NanoGPT | $0.75 | $3.75 | $0.075 | 1.0M |
| Ofox | $0.75 | $3.75 | $0.075 | 1.0M |
| OpenRouter | $0.75 | $3.75 | $0.075 | 1.0M |
| Opper | $0.75 | $3.75 | $0.075 | 1.0M |
| Requesty | $0.75 | $3.75 | $0.075 | 1.0M |
| Tempr Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| Vercel AI Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| Vivgrid | $0.75 | $3.75 | $0.075 | 1.0M |
| Requesty (eu) | $0.825 | $4.125 | $0.0825 | 1.0M |
| Venice AI | $0.9375 | $4.6875 | $0.0938 | 1.0M |
| OpenCode Zen | $1.5 | $7.5 | $0.15 | 1.0M |

## Summary

- Cheapest input: $0.75 per 1M tokens (302.AI)
- Cheapest output: $3.75 per 1M tokens (302.AI)
- First-party: $3.75 per 1M output tokens (Google)
- Free offers: Kenari
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-08-13
- Inputs: audio, image, pdf, text, video

## FAQ

### What is the cheapest Gemini 3.7 Flash API?

As of Oct 4, 2026, 302.AI has the lowest Gemini 3.7 Flash output price at $3.75 per 1M tokens, and 302.AI has the lowest input price at $0.75 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Gemini 3.7 Flash cost on Google?

Google charges $0.75 per 1M input tokens and $3.75 per 1M output tokens for Gemini 3.7 Flash.

### How many providers offer Gemini 3.7 Flash?

24 providers list Gemini 3.7 Flash on Sovyron; 25 of them sell it at a metered per-token price.

### Is Gemini 3.7 Flash free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is Gemini 3.7 Flash included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Gemini 3.7 Flash?

Gemini 3.7 Flash supports a 1.0M-token context window and up to 66k output tokens.

HTML page: https://sovyron.com/models/gemini-3-7-flash/
Full dataset: https://sovyron.com/data/catalog.json

---

# Inkling API prices

Inkling (ling) — 1.0M context, 1.0M max output.
25 metered per-token offers from 22 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Deep Infra | $0.95 | $4.05 | $0.16 | 524k |
| Eden AI | $0.95 | $4.05 | $0.16 | 524k |
| Kilo Gateway | $0.95 | $4.05 | $0.16 | 524k |
| DevPass (LLM Gateway) | $0.95 | $4.05 | $0.16 | 524k |
| LLM Gateway | $0.95 | $4.05 | $0.16 | 524k |
| OpenRouter | $0.95 | $4.05 | $0.16 | 524k |
| Baseten | $1 | $4.05 | — | 1.0M |
| Eden AI | $1 | $4.05 | $0.1 | 1.0M |
| Eden AI | $1 | $4.05 | $0.17 | 1.0M |
| Eden AI | $1 | $4.05 | $0.17 | 524k |
| Fireworks AI | $1 | $4.05 | $0.17 | 1.0M |
| Hugging Face | $1 | $4.05 | — | 1.0M |
| Merge Gateway | $1 | $4.05 | $0.17 | 1.0M |
| NanoGPT | $1 | $4.05 | $0.17 | 1.0M |
| Neon | $1 | $4.05 | $0.17 | 1.0M |
| Together AI | $1 | $4.05 | $0.17 | 524k |
| Vercel AI Gateway | $1 | $4.05 | $0.17 | 256k |
| Charm Hyper | $1.0888 | $4.4096 | $0.1851 | 1.0M |
| Modal | $1.2 | $5 | $0.27 | 1.0M |
| Venice AI | $1.25 | $5.0625 | $0.2125 | 524k |
| Impossibl | $1.87 | $4.68 | $0.374 | 66k |
| LLMTR | $1.87 | $4.68 | — | 262k |
| Requesty | $1.87 | $4.68 | $0.374 | 66k |
| Thinking Machines | $1.87 | $4.68 | $0.374 | 66k |
| Abacus | $3.74 | $9.36 | $0.748 | 262k |

## Summary

- Cheapest input: $0.95 per 1M tokens (Deep Infra)
- Cheapest output: $4.05 per 1M tokens (Deep Infra)
- First-party: not listed separately
- Free offers: OpenRouter
- Subscription plans (not per-token): none
- Released: 2026-07-15
- Inputs: audio, image, pdf, text

## FAQ

### What is the cheapest Inkling API?

As of Oct 4, 2026, Deep Infra has the lowest Inkling output price at $4.05 per 1M tokens, and Deep Infra has the lowest input price at $0.95 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Inkling?

22 providers list Inkling on Sovyron; 25 of them sell it at a metered per-token price.

### Is Inkling free?

1 provider(s) list a free-tier offer: OpenRouter. Free tiers usually have rate limits.

### What is the context window of Inkling?

Inkling supports a 1.0M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/inkling/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-4o API prices

GPT-4o (gpt) — 128k context, 16k max output.
41 metered per-token offers from 22 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Cloudflare AI Gateway | $1.25 | $5 | $0.625 | 128k |
| Ofox | $2 | $8 | $1 | 128k |
| 302.AI | $2.5 | $10 | — | 128k |
| Abacus | $2.5 | $10 | $1.25 | 128k |
| Abacus | $2.5 | $10 | — | 128k |
| DigitalOcean | $2.5 | $10 | $1.25 | 128k |
| Eden AI | $2.5 | $10 | $1.25 | 128k |
| Eden AI | $2.5 | $10 | $1.25 | 128k |
| Eden AI | $2.5 | $10 | $1.25 | 128k |
| FrogBot | $2.5 | $10 | $1.25 | 128k |
| Helicone | $2.5 | $10 | $1.25 | 128k |
| Impossibl | $2.5 | $10 | $1.25 | 128k |
| Kilo Gateway | $2.5 | $10 | $1.25 | 128k |
| Kilo Gateway | $2.5 | $10 | $1.25 | 128k |
| Kilo Gateway | $2.5 | $10 | $1.25 | 128k |
| DevPass (LLM Gateway) | $2.5 | $10 | $1.25 | 128k |
| LLM Gateway | $2.5 | $10 | $1.25 | 128k |
| LLM Gateway | $2.5 | $10 | $1.25 | 128k |
| Merge Gateway | $2.5 | $10 | $1.25 | 128k |
| Merge Gateway | $2.5 | $10 | $1.25 | 128k |
| Merge Gateway | $2.5 | $10 | $1.25 | 128k |
| NanoGPT | $2.5 | $10 | $1.25 | 128k |
| NanoGPT | $2.5 | $10 | $1.25 | 128k |
| NanoGPT | $2.5 | $10 | $1.25 | 128k |
| OpenAI | $2.5 | $10 | $1.25 | 128k |
| OpenAI | $2.5 | $10 | $1.25 | 128k |
| OpenAI | $2.5 | $10 | $1.25 | 128k |
| OpenRouter | $2.5 | $10 | $1.25 | 128k |
| OpenRouter | $2.5 | $10 | $1.25 | 128k |
| OpenRouter | $2.5 | $10 | $1.25 | 128k |
| OrcaRouter | $2.5 | $10 | $1.25 | 128k |
| OrcaRouter | $2.5 | $10 | $1.25 | 128k |
| OrcaRouter | $2.5 | $10 | $1.25 | 128k |
| Pioneer | $2.5 | $10 | $1.25 | 128k |
| Vercel AI Gateway | $2.5 | $10 | $1.25 | 128k |
| Cortecs | $2.659 | $10.635 | $1.33 | 128k |
| Venice AI | $3.125 | $12.5 | — | 128k |
| Kilo Gateway | $5 | $15 | — | 128k |
| Merge Gateway | $5 | $15 | — | 128k |
| OpenRouter | $5 | $15 | — | 128k |
| OrcaRouter | $5 | $15 | — | 128k |

## Summary

- Cheapest input: $1.25 per 1M tokens (Cloudflare AI Gateway)
- Cheapest output: $5 per 1M tokens (Cloudflare AI Gateway)
- First-party: $10 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-05-13
- Inputs: audio, image, pdf, text

## FAQ

### What is the cheapest GPT-4o API?

As of Oct 4, 2026, Cloudflare AI Gateway has the lowest GPT-4o output price at $5 per 1M tokens, and Cloudflare AI Gateway has the lowest input price at $1.25 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-4o cost on OpenAI?

OpenAI charges $2.5 per 1M input tokens and $10 per 1M output tokens for GPT-4o.

### How many providers offer GPT-4o?

22 providers list GPT-4o on Sovyron; 41 of them sell it at a metered per-token price.

### Is GPT-4o free?

No provider in the Sovyron catalog lists a free tier for GPT-4o.

### What is the context window of GPT-4o?

GPT-4o supports a 128k-token context window and up to 16k output tokens.

HTML page: https://sovyron.com/models/gpt-4o/
Full dataset: https://sovyron.com/data/catalog.json

---

# Gemini 3.8 Flash API prices

Gemini 3.8 Flash (gemini-flash) — 1.0M context, 1.0M max output.
24 metered per-token offers from 23 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| 302.AI | $0.75 | $3.75 | — | 1.0M |
| AIHubMix | $0.75 | $3.75 | $0.075 | 1.0M |
| CrossModel | $0.75 | $3.75 | $0.075 | 1.0M |
| Eden AI | $0.75 | $3.75 | $0.075 | 1.0M |
| Eden AI | $0.75 | $3.75 | $0.075 | 1.0M |
| Google | $0.75 | $3.75 | $0.075 | 1.0M |
| Vertex | $0.75 | $3.75 | $0.075 | 1.0M |
| Kilo Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| DevPass (LLM Gateway) | $0.75 | $3.75 | $0.075 | 1.0M |
| LLM Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| LLM Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| Merge Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| NanoGPT | $0.75 | $3.75 | $0.075 | 1.0M |
| Ofox | $0.75 | $3.75 | $0.075 | 1.0M |
| OpenRouter | $0.75 | $3.75 | $0.075 | 1.0M |
| Requesty | $0.75 | $3.75 | $0.075 | 1.0M |
| Tempr Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| Vercel AI Gateway | $0.75 | $3.75 | $0.075 | 1.0M |
| Vivgrid | $0.75 | $3.75 | $0.15 | 1.0M |
| Cortecs | $0.825 | $4.125 | $0.082 | 1.0M |
| Opper | $0.825 | $4.125 | $0.0825 | 1.0M |
| Requesty (eu) | $0.825 | $4.125 | $0.0825 | 1.0M |
| Venice AI | $0.9375 | $4.6875 | $0.0938 | 1.0M |
| OpenCode Zen | $1.5 | $7.5 | $0.15 | 1.0M |

## Summary

- Cheapest input: $0.75 per 1M tokens (302.AI)
- Cheapest output: $3.75 per 1M tokens (302.AI)
- First-party: $3.75 per 1M output tokens (Google)
- Free offers: none
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-09-02
- Inputs: audio, image, pdf, text, video

## FAQ

### What is the cheapest Gemini 3.8 Flash API?

As of Oct 4, 2026, 302.AI has the lowest Gemini 3.8 Flash output price at $3.75 per 1M tokens, and 302.AI has the lowest input price at $0.75 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Gemini 3.8 Flash cost on Google?

Google charges $0.75 per 1M input tokens and $3.75 per 1M output tokens for Gemini 3.8 Flash.

### How many providers offer Gemini 3.8 Flash?

23 providers list Gemini 3.8 Flash on Sovyron; 24 of them sell it at a metered per-token price.

### Is Gemini 3.8 Flash free?

No provider in the Sovyron catalog lists a free tier for Gemini 3.8 Flash.

### Is Gemini 3.8 Flash included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Gemini 3.8 Flash?

Gemini 3.8 Flash supports a 1.0M-token context window and up to 1.0M output tokens.

HTML page: https://sovyron.com/models/gemini-3-8-flash/
Full dataset: https://sovyron.com/data/catalog.json

---

# Qwen3.6 27B API prices

Qwen3.6 27B (qwen) — 262k context, 262k max output.
22 metered per-token offers from 24 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| CrofAI | $0.2 | $1.5 | $0.04 | 262k |
| STACKIT | $0.53 | $0.76 | — | 262k |
| Pioneer | $0.6 | $0.6 | $0.6 | 33k |
| NanoGPT | $0.203 | $2.24 | $0.1015 | 260k |
| Merge Gateway | $0.289 | $2.4 | — | 131k |
| EmpirioLabs AI | $0.4126 | $2.4754 | $0.4126 | 256k |
| Ofox | $0.43 | $2.57 | — | 256k |
| Kilo Gateway | $0.45 | $2.7 | — | 262k |
| SiliconFlow | $0.3 | $3.2 | — | 262k |
| Abacus | $0.32 | $3.2 | — | 262k |
| ai& | $0.32 | $3.2 | $0.2 | 262k |
| Ambient | $0.32 | $3.2 | $0.16 | 33k |
| Deep Infra | $0.32 | $3.2 | — | 262k |
| OpenRouter | $0.32 | $3.2 | — | 262k |
| Cortecs | $0.446 | $3.008 | — | 262k |
| Hugging Face | $0.47 | $3.19 | — | 262k |
| OVHcloud AI Endpoints | $0.47 | $3.19 | — | 262k |
| Groq | $0.6 | $3 | $0.3 | 131k |
| Synthetic | $0.45 | $3.6 | $0.45 | 262k |
| Alibaba | $0.6 | $3.6 | — | 262k |
| Ofox | $0.6 | $3.6 | — | 256k |
| CoreWeave | $0.6 | $3.6 | $0.12 | 262k |

## Summary

- Cheapest input: $0.2 per 1M tokens (CrofAI)
- Cheapest output: $0.6 per 1M tokens (Pioneer)
- First-party: $3.6 per 1M output tokens (Alibaba)
- Free offers: Pendra, QVAC
- Subscription plans (not per-token): none
- Released: 2026-04-22
- Inputs: audio, image, pdf, text, video

## FAQ

### What is the cheapest Qwen3.6 27B API?

As of Oct 4, 2026, Pioneer has the lowest Qwen3.6 27B output price at $0.6 per 1M tokens, and CrofAI has the lowest input price at $0.2 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Qwen3.6 27B cost on Alibaba?

Alibaba charges $0.6 per 1M input tokens and $3.6 per 1M output tokens for Qwen3.6 27B.

### How many providers offer Qwen3.6 27B?

24 providers list Qwen3.6 27B on Sovyron; 22 of them sell it at a metered per-token price.

### Is Qwen3.6 27B free?

2 provider(s) list a free-tier offer: Pendra, QVAC. Free tiers usually have rate limits.

### What is the context window of Qwen3.6 27B?

Qwen3.6 27B supports a 262k-token context window and up to 262k output tokens.

HTML page: https://sovyron.com/models/qwen3-6-27b/
Full dataset: https://sovyron.com/data/catalog.json

---

# Qwen3.8 Flash API prices

Qwen3.8 Flash (qwen) — 1.0M context, 131k max output.
23 metered per-token offers from 25 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| AIHubMix | $0.1126 | $0.38 | $0.0141 | 1.0M |
| Ofox | $0.11 | $0.39 | $0.011 | 1.0M |
| Deep Infra | $0.113 | $0.382 | $0.0141 | 1.0M |
| Vancine | $0.12 | $0.38 | $0.013 | 1.0M |
| Alibaba (China) | $0.1187 | $0.4007 | $0.0119 | 1.0M |
| CrossModel | $0.13 | $0.43 | $0.016 | 1.0M |
| NanoGPT | $0.14 | $0.42 | $0.016 | 992k |
| Alibaba | $0.15 | $0.47 | $0.016 | 1.0M |
| Eden AI | $0.15 | $0.47 | $0.016 | 1.0M |
| Charm Hyper | $0.15 | $0.47 | $0.016 | 1.0M |
| Kilo Gateway | $0.15 | $0.47 | $0.016 | 1.0M |
| DevPass (LLM Gateway) | $0.15 | $0.47 | $0.016 | 1.0M |
| LLM Gateway | $0.15 | $0.47 | $0.016 | 984k |
| LLM Gateway | $0.15 | $0.47 | $0.016 | 1.0M |
| Merge Gateway | $0.15 | $0.47 | $0.016 | 977k |
| Ofox | $0.15 | $0.47 | $0.016 | 1.0M |
| OpenCode Zen | $0.15 | $0.47 | $0.016 | 1.0M |
| OpenCode Go | $0.15 | $0.47 | $0.016 | 1.0M |
| OpenRouter | $0.15 | $0.47 | $0.016 | 1.0M |
| EmpirioLabs AI | $0.16 | $0.47 | $0.16 | 1.0M |
| GMI Cloud | $0.16 | $0.47 | $0.016 | 1.0M |
| Requesty | $0.16 | $0.47 | $0.016 | 1.0M |
| 302.AI | $0.18 | $0.564 | — | 1.0M |

## Summary

- Cheapest input: $0.11 per 1M tokens (Ofox)
- Cheapest output: $0.38 per 1M tokens (Vancine)
- First-party: $0.47 per 1M output tokens (Alibaba)
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China), NaN, SCNet Token Plan
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China), SCNet Token Plan
- Released: 2026-08-26
- Inputs: image, text, video

## FAQ

### What is the cheapest Qwen3.8 Flash API?

As of Oct 4, 2026, Vancine has the lowest Qwen3.8 Flash output price at $0.38 per 1M tokens, and Ofox has the lowest input price at $0.11 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Qwen3.8 Flash cost on Alibaba?

Alibaba charges $0.15 per 1M input tokens and $0.47 per 1M output tokens for Qwen3.8 Flash.

### How many providers offer Qwen3.8 Flash?

25 providers list Qwen3.8 Flash on Sovyron; 23 of them sell it at a metered per-token price.

### Is Qwen3.8 Flash free?

1 provider(s) list a free-tier offer: NaN. Free tiers usually have rate limits.

### Is Qwen3.8 Flash included in a subscription plan?

Yes. 4 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of Qwen3.8 Flash?

Qwen3.8 Flash supports a 1.0M-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/qwen3-8-flash/
Full dataset: https://sovyron.com/data/catalog.json

---

# o3 API prices

o3 (o) — 200k context, 131k max output.
21 metered per-token offers from 22 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Poe | $1.8 | $7.2 | $0.45 | 200k |
| 302.AI | $2 | $8 | — | 200k |
| Abacus | $2 | $8 | $0.5 | 200k |
| AIHubMix | $2 | $8 | $0.5 | 200k |
| Azure | $2 | $8 | $0.5 | 200k |
| Azure Cognitive Services | $2 | $8 | $0.5 | 200k |
| Cloudflare AI Gateway | $2 | $8 | $0.5 | 200k |
| DigitalOcean | $2 | $8 | $0.5 | 200k |
| Eden AI | $2 | $8 | $0.5 | 200k |
| Helicone | $2 | $8 | $0.5 | 200k |
| Impossibl | $2 | $8 | $0.5 | 200k |
| Kilo Gateway | $2 | $8 | $0.5 | 200k |
| DevPass (LLM Gateway) | $2 | $8 | $0.5 | 200k |
| LLM Gateway | $2 | $8 | $0.5 | 200k |
| Merge Gateway | $2 | $8 | $0.5 | 200k |
| NanoGPT | $2 | $8 | $1 | 200k |
| NEAR AI Cloud | $2 | $8 | $0.5 | 200k |
| OpenAI | $2 | $8 | $0.5 | 200k |
| OpenRouter | $2 | $8 | $0.5 | 200k |
| Vercel AI Gateway | $2 | $8 | $0.5 | 200k |
| Jiekou.AI | $10 | $40 | — | 131k |

## Summary

- Cheapest input: $1.8 per 1M tokens (Poe)
- Cheapest output: $7.2 per 1M tokens (Poe)
- First-party: $8 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-04-16
- Inputs: image, pdf, text

## FAQ

### What is the cheapest o3 API?

As of Oct 4, 2026, Poe has the lowest o3 output price at $7.2 per 1M tokens, and Poe has the lowest input price at $1.8 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does o3 cost on OpenAI?

OpenAI charges $2 per 1M input tokens and $8 per 1M output tokens for o3.

### How many providers offer o3?

22 providers list o3 on Sovyron; 21 of them sell it at a metered per-token price.

### Is o3 free?

No provider in the Sovyron catalog lists a free tier for o3.

### What is the context window of o3?

o3 supports a 200k-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/o3/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.2 Codex API prices

GPT-5.2 Codex (gpt-codex) — 400k context, 128k max output.
20 metered per-token offers from 20 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| QiHang | $0.14 | $1.14 | — | 400k |
| Ofox | $1.4 | $11.2 | $0.144 | 400k |
| Poe | $1.6 | $13 | $0.16 | 400k |
| Abacus | $1.75 | $14 | $0.175 | 400k |
| AIHubMix | $1.75 | $14 | $0.175 | 400k |
| Azure | $1.75 | $14 | $0.175 | 400k |
| Azure Cognitive Services | $1.75 | $14 | $0.175 | 400k |
| Eden AI | $1.75 | $14 | $0.175 | 272k |
| Impossibl | $1.75 | $14 | $0.175 | 400k |
| Jiekou.AI | $1.75 | $14 | — | 400k |
| Kilo Gateway | $1.75 | $14 | $0.175 | 400k |
| DevPass (LLM Gateway) | $1.75 | $14 | $0.175 | 400k |
| LLM Gateway | $1.75 | $14 | $0.175 | 400k |
| NanoGPT | $1.75 | $14 | $0.175 | 400k |
| OpenCode Zen | $1.75 | $14 | $0.175 | 400k |
| OpenRouter | $1.75 | $14 | $0.175 | 400k |
| OrcaRouter | $1.75 | $14 | $0.175 | 400k |
| Vercel AI Gateway | $1.75 | $14 | $0.175 | 400k |
| Vivgrid | $1.75 | $14 | $0.175 | 400k |
| ZenMux | $1.75 | $14 | $0.17 | 400k |

## Summary

- Cheapest input: $0.14 per 1M tokens (QiHang)
- Cheapest output: $1.14 per 1M tokens (QiHang)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-12-11
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.2 Codex API?

As of Oct 4, 2026, QiHang has the lowest GPT-5.2 Codex output price at $1.14 per 1M tokens, and QiHang has the lowest input price at $0.14 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer GPT-5.2 Codex?

20 providers list GPT-5.2 Codex on Sovyron; 20 of them sell it at a metered per-token price.

### Is GPT-5.2 Codex free?

No provider in the Sovyron catalog lists a free tier for GPT-5.2 Codex.

### What is the context window of GPT-5.2 Codex?

GPT-5.2 Codex supports a 400k-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-2-codex/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.4 Pro API prices

GPT-5.4 Pro (gpt-pro) — 1.1M context, 128k max output.
21 metered per-token offers from 20 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $24 | $144 | — | 1.1M |
| Poe | $27 | $160 | — | 1.1M |
| Azure | $30 | $180 | — | 1.1M |
| Azure Cognitive Services | $30 | $180 | — | 1.1M |
| Cloudflare AI Gateway | $30 | $180 | — | 1.0M |
| DigitalOcean | $30 | $180 | — | 1.1M |
| Eden AI | $30 | $180 | — | 1.1M |
| Impossibl | $30 | $180 | $3 | 1.1M |
| Kilo Gateway | $30 | $180 | — | 1.1M |
| DevPass (LLM Gateway) | $30 | $180 | — | 1.1M |
| LLM Gateway | $30 | $180 | — | 1.1M |
| LLM Gateway | $30 | $180 | — | 1.1M |
| OpenAI | $30 | $180 | — | 1.1M |
| OpenCode Zen | $30 | $180 | $30 | 1.1M |
| OpenRouter | $30 | $180 | — | 1.1M |
| Opper | $30 | $180 | — | 1.1M |
| OrcaRouter | $30 | $180 | — | 1.1M |
| Requesty | $30 | $180 | $30 | 1.1M |
| Vercel AI Gateway | $30 | $180 | — | 1.1M |
| Venice AI | $37.5 | $225 | — | 1.0M |
| ZenMux | $45 | $225 | — | 1.1M |

## Summary

- Cheapest input: $24 per 1M tokens (Ofox)
- Cheapest output: $144 per 1M tokens (Ofox)
- First-party: $180 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-03-05
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.4 Pro API?

As of Oct 4, 2026, Ofox has the lowest GPT-5.4 Pro output price at $144 per 1M tokens, and Ofox has the lowest input price at $24 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5.4 Pro cost on OpenAI?

OpenAI charges $30 per 1M input tokens and $180 per 1M output tokens for GPT-5.4 Pro.

### How many providers offer GPT-5.4 Pro?

20 providers list GPT-5.4 Pro on Sovyron; 21 of them sell it at a metered per-token price.

### Is GPT-5.4 Pro free?

No provider in the Sovyron catalog lists a free tier for GPT-5.4 Pro.

### What is the context window of GPT-5.4 Pro?

GPT-5.4 Pro supports a 1.1M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-4-pro/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.5 Pro API prices

GPT-5.5 Pro (gpt-pro) — 1.1M context, 128k max output.
20 metered per-token offers from 20 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Poe | $27.2727 | $163.6364 | — | 400k |
| AIHubMix | $30 | $180 | — | 1.1M |
| Cloudflare AI Gateway | $30 | $180 | — | 1.0M |
| CrossModel | $30 | $180 | — | 1.1M |
| Eden AI | $30 | $180 | — | 1.1M |
| FastRouter | $30 | $180 | — | 1.1M |
| Impossibl | $30 | $180 | $3 | 1.1M |
| Kilo Gateway | $30 | $180 | — | 1.1M |
| DevPass (LLM Gateway) | $30 | $180 | — | 1.1M |
| LLM Gateway | $30 | $180 | — | 1.1M |
| Neon | $30 | $180 | — | 1.1M |
| OpenAI | $30 | $180 | — | 1.1M |
| OpenCode Zen | $30 | $180 | $30 | 1.1M |
| OpenRouter | $30 | $180 | — | 1.1M |
| Opper | $30 | $180 | — | 1.1M |
| OrcaRouter | $30 | $180 | — | 1.1M |
| Requesty | $30 | $180 | — | 1.1M |
| Vercel AI Gateway | $30 | $180 | — | 1.0M |
| ZenMux | $30 | $180 | — | 1.1M |
| Venice AI | $37.5 | $225 | — | 1.0M |

## Summary

- Cheapest input: $27.2727 per 1M tokens (Poe)
- Cheapest output: $163.6364 per 1M tokens (Poe)
- First-party: $180 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-04-23
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.5 Pro API?

As of Oct 4, 2026, Poe has the lowest GPT-5.5 Pro output price at $163.6364 per 1M tokens, and Poe has the lowest input price at $27.2727 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-5.5 Pro cost on OpenAI?

OpenAI charges $30 per 1M input tokens and $180 per 1M output tokens for GPT-5.5 Pro.

### How many providers offer GPT-5.5 Pro?

20 providers list GPT-5.5 Pro on Sovyron; 20 of them sell it at a metered per-token price.

### Is GPT-5.5 Pro free?

No provider in the Sovyron catalog lists a free tier for GPT-5.5 Pro.

### What is the context window of GPT-5.5 Pro?

GPT-5.5 Pro supports a 1.1M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-5-pro/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-6.1 Sol API prices

GPT-6.1 Sol (gpt-sol) — 1.1M context, 128k max output.
24 metered per-token offers from 21 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Amazon Bedrock (global) | $2 | $10 | $0.1 | 1.1M |
| Azure | $2 | $10 | $0.1 | 1.1M |
| Azure Cognitive Services | $2 | $10 | $0.1 | 1.1M |
| CrossModel | $2 | $10 | $0.1 | 1.1M |
| DigitalOcean | $2 | $10 | $0.1 | 1.1M |
| Eden AI | $2 | $10 | $0.1 | 1.1M |
| Kilo Gateway | $2 | $10 | $0.1 | 1.1M |
| DevPass (LLM Gateway) | $2 | $10 | $0.1 | 1.1M |
| LLM Gateway | $2 | $10 | $0.1 | 1.1M |
| LLM Gateway | $2 | $10 | $0.1 | 1.1M |
| Merge Gateway | $2 | $10 | $0.1 | 1.1M |
| NanoGPT | $2 | $10 | $0.1 | 1.1M |
| Ofox | $2 | $10 | $0.1 | 1.1M |
| OpenAI | $2 | $10 | $0.1 | 1.1M |
| OpenCode Zen | $2 | $10 | $0.1 | 1.1M |
| OpenRouter | $2 | $10 | $0.1 | 1.1M |
| Requesty | $2 | $10 | $0.1 | 1.1M |
| Vercel AI Gateway | $2 | $10 | $0.1 | 1.1M |
| Vivgrid | $2 | $10 | $0.2 | 1.1M |
| Amazon Bedrock | $2.2 | $11 | $0.11 | 1.1M |
| Amazon Bedrock (us) | $2.2 | $11 | $0.11 | 1.1M |
| Cortecs | $2.4 | $11.999 | $0.12 | 1.1M |
| Requesty (eu) | $2.4 | $12 | $0.12 | 1.1M |
| Venice AI | $2.5 | $12.5 | $0.125 | 1.1M |

## Summary

- Cheapest input: $2 per 1M tokens (Amazon Bedrock)
- Cheapest output: $10 per 1M tokens (Amazon Bedrock)
- First-party: $10 per 1M output tokens (OpenAI)
- Free offers: none
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-09-29
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-6.1 Sol API?

As of Oct 4, 2026, Amazon Bedrock has the lowest GPT-6.1 Sol output price at $10 per 1M tokens, and Amazon Bedrock has the lowest input price at $2 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GPT-6.1 Sol cost on OpenAI?

OpenAI charges $2 per 1M input tokens and $10 per 1M output tokens for GPT-6.1 Sol.

### How many providers offer GPT-6.1 Sol?

21 providers list GPT-6.1 Sol on Sovyron; 24 of them sell it at a metered per-token price.

### Is GPT-6.1 Sol free?

No provider in the Sovyron catalog lists a free tier for GPT-6.1 Sol.

### Is GPT-6.1 Sol included in a subscription plan?

Yes. 2 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of GPT-6.1 Sol?

GPT-6.1 Sol supports a 1.1M-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-6-1-sol/
Full dataset: https://sovyron.com/data/catalog.json

---

# Grok 4.7 API prices

Grok 4.7 (grok) — 524k context, 524k max output.
22 metered per-token offers from 21 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| NanoGPT | $1.6 | $4.8 | $0.4 | 500k |
| 302.AI | $2 | $6 | $0.5 | 500k |
| Amazon Bedrock (global) | $2 | $6 | $0.5 | 500k |
| Cloudflare AI Gateway | $2 | $6 | $0.5 | 500k |
| CrossModel | $2 | $6 | $0.5 | 500k |
| Eden AI | $2 | $6 | $0.5 | 500k |
| Kilo Gateway | $2 | $6 | $0.5 | 500k |
| DevPass (LLM Gateway) | $2 | $6 | $0.5 | 524k |
| LLM Gateway | $2 | $6 | $0.5 | 524k |
| LLM Gateway | $2 | $6 | $0.5 | 500k |
| Merge Gateway | $2 | $6 | $0.5 | 500k |
| Ofox | $2 | $6 | $0.5 | 500k |
| OpenCode Zen | $2 | $6 | $0.5 | 500k |
| OpenCode Go | $2 | $6 | $0.5 | 500k |
| OpenRouter | $2 | $6 | $0.5 | 500k |
| Requesty | $2 | $6 | $0.5 | 500k |
| Tempr Gateway | $2 | $6 | $0.5 | 500k |
| Vercel AI Gateway | $2 | $6 | $0.5 | 500k |
| xAI | $2 | $6 | $0.5 | 500k |
| AIHubMix | $2.2 | $6.6 | $0.55 | 500k |
| Amazon Bedrock (us) | $2.2 | $6.6 | $0.55 | 500k |
| Venice AI | $2.27 | $6.8 | $0.57 | 500k |

## Summary

- Cheapest input: $1.6 per 1M tokens (NanoGPT)
- Cheapest output: $4.8 per 1M tokens (NanoGPT)
- First-party: $6 per 1M output tokens (xAI)
- Free offers: none
- Subscription plans (not per-token): GitHub Copilot
- Released: 2026-09-21
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Grok 4.7 API?

As of Oct 4, 2026, NanoGPT has the lowest Grok 4.7 output price at $4.8 per 1M tokens, and NanoGPT has the lowest input price at $1.6 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Grok 4.7 cost on xAI?

xAI charges $2 per 1M input tokens and $6 per 1M output tokens for Grok 4.7.

### How many providers offer Grok 4.7?

21 providers list Grok 4.7 on Sovyron; 22 of them sell it at a metered per-token price.

### Is Grok 4.7 free?

No provider in the Sovyron catalog lists a free tier for Grok 4.7.

### Is Grok 4.7 included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is GitHub Copilot Pro at $10/month.

### What is the context window of Grok 4.7?

Grok 4.7 supports a 524k-token context window and up to 524k output tokens.

HTML page: https://sovyron.com/models/grok-4-7/
Full dataset: https://sovyron.com/data/catalog.json

---

# MiniMax-M2.1 API prices

MiniMax-M2.1 (minimax) — 205k context, 196k max output.
21 metered per-token offers from 24 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| DevPass (LLM Gateway) | $0.27 | $1.1 | — | 205k |
| LLM Gateway | $0.27 | $1.1 | — | 197k |
| Meganova | $0.28 | $1.2 | — | 197k |
| 302.AI | $0.3 | $1.2 | — | 205k |
| Amazon Bedrock | $0.3 | $1.2 | — | 197k |
| Eden AI | $0.3 | $1.2 | $0.03 | 205k |
| Hugging Face | $0.3 | $1.2 | — | 205k |
| Jiekou.AI | $0.3 | $1.2 | — | 205k |
| Kilo Gateway | $0.3 | $1.2 | $0.03 | 205k |
| LLM Gateway | $0.3 | $1.2 | $0.03 | 205k |
| Merge Gateway | $0.3 | $1.2 | $0.03 | 205k |
| MiniMax (minimax.io) | $0.3 | $1.2 | $0.03 | 205k |
| MiniMax (minimax.cn) | $0.3 | $1.2 | $0.03 | 205k |
| NovitaAI | $0.3 | $1.2 | $0.03 | 205k |
| Ofox | $0.3 | $1.2 | $0.03 | 205k |
| OpenRouter | $0.3 | $1.2 | $0.03 | 205k |
| Vercel AI Gateway | $0.3 | $1.2 | $0.03 | 205k |
| ZenMux | $0.3 | $1.2 | $0.03 | 204k |
| NanoGPT | $0.33 | $1.32 | $0.165 | 200k |
| Cortecs | $0.359 | $1.435 | — | 196k |
| Moark | $2.1 | $8.4 | $2.1 | 205k |

## Summary

- Cheapest input: $0.27 per 1M tokens (DevPass (LLM Gateway))
- Cheapest output: $1.1 per 1M tokens (DevPass (LLM Gateway))
- First-party: $1.2 per 1M output tokens (MiniMax (minimax.io))
- Free offers: MiniMax Token Plan (minimax.cn), MiniMax Token Plan (minimax.io)
- Subscription plans (not per-token): MiniMax Token Plan (minimax.cn), MiniMax Token Plan (minimax.io)
- Released: 2025-12-23
- Inputs: text

## FAQ

### What is the cheapest MiniMax-M2.1 API?

As of Oct 4, 2026, DevPass (LLM Gateway) has the lowest MiniMax-M2.1 output price at $1.1 per 1M tokens, and DevPass (LLM Gateway) has the lowest input price at $0.27 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does MiniMax-M2.1 cost on MiniMax (minimax.io)?

MiniMax (minimax.io) charges $0.3 per 1M input tokens and $1.2 per 1M output tokens for MiniMax-M2.1.

### How many providers offer MiniMax-M2.1?

24 providers list MiniMax-M2.1 on Sovyron; 21 of them sell it at a metered per-token price.

### Is MiniMax-M2.1 free?

No provider in the Sovyron catalog lists a free tier for MiniMax-M2.1.

### Is MiniMax-M2.1 included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is MiniMax Code Plus at $20/month.

### What is the context window of MiniMax-M2.1?

MiniMax-M2.1 supports a 205k-token context window and up to 196k output tokens.

HTML page: https://sovyron.com/models/minimax-m2-1/
Full dataset: https://sovyron.com/data/catalog.json

---

# Qwen3.6 Plus API prices

Qwen3.6 Plus (qwen) — 1.0M context, 500k max output.
21 metered per-token offers from 24 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Merge Gateway | $0.276 | $1.651 | $0.0552 | 1.0M |
| AIHubMix | $0.28 | $1.69 | $0.0282 | 991k |
| 302.AI | $0.3 | $1.8 | — | 1.0M |
| CrossModel | $0.32 | $1.88 | $0.032 | 1.0M |
| Kilo Gateway | $0.325 | $1.95 | — | 1.0M |
| OpenRouter | $0.325 | $1.95 | — | 1.0M |
| Pioneer | $0.325 | $1.95 | $0.065 | 1.0M |
| Alibaba | $0.5 | $3 | $0.05 | 1.0M |
| Alibaba (China) | $0.5 | $3 | $0.05 | 1.0M |
| Auriko | $0.5 | $3 | $0.1 | 1.0M |
| EmpirioLabs AI | $0.5 | $3 | $0.5 | 1.0M |
| DevPass (LLM Gateway) | $0.5 | $3 | $0.05 | 984k |
| LLM Gateway | $0.5 | $3 | $0.05 | 984k |
| LLMTR | $0.5 | $3 | — | 1.0M |
| Ofox | $0.5 | $3 | $0.05 | 1.0M |
| Ofox | $0.5 | $3 | $0.05 | 1.0M |
| OpenCode Zen | $0.5 | $3 | $0.05 | 262k |
| OrcaRouter | $0.5 | $3 | $0.05 | 1.0M |
| Requesty | $0.5 | $3 | $0.05 | 1.0M |
| Together AI | $0.5 | $3 | — | 1.0M |
| ZenMux | $0.5 | $3 | $0.05 | 1.0M |

## Summary

- Cheapest input: $0.276 per 1M tokens (Merge Gateway)
- Cheapest output: $1.651 per 1M tokens (Merge Gateway)
- First-party: $3 per 1M output tokens (Alibaba)
- Free offers: Alibaba Coding Plan, Alibaba Coding Plan (China), Alibaba Token Plan, Alibaba Token Plan (China)
- Subscription plans (not per-token): Alibaba Coding Plan, Alibaba Coding Plan (China), Alibaba Token Plan, Alibaba Token Plan (China)
- Released: 2026-04-02
- Inputs: image, text, video

## FAQ

### What is the cheapest Qwen3.6 Plus API?

As of Oct 4, 2026, Merge Gateway has the lowest Qwen3.6 Plus output price at $1.651 per 1M tokens, and Merge Gateway has the lowest input price at $0.276 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Qwen3.6 Plus cost on Alibaba?

Alibaba charges $0.5 per 1M input tokens and $3 per 1M output tokens for Qwen3.6 Plus.

### How many providers offer Qwen3.6 Plus?

24 providers list Qwen3.6 Plus on Sovyron; 21 of them sell it at a metered per-token price.

### Is Qwen3.6 Plus free?

No provider in the Sovyron catalog lists a free tier for Qwen3.6 Plus.

### Is Qwen3.6 Plus included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of Qwen3.6 Plus?

Qwen3.6 Plus supports a 1.0M-token context window and up to 500k output tokens.

HTML page: https://sovyron.com/models/qwen3-6-plus/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-4.1 nano API prices

GPT-4.1 nano (gpt-nano) — 1.0M context, 33k max output.
20 metered per-token offers from 19 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| SAP AI Core | $0.08 | $0.26 | — | 1.0M |
| Poe | $0.09 | $0.36 | $0.022 | 1.0M |
| Helicone | $0.1 | $0.4 | $0.025 | 1.0M |
| 302.AI | $0.1 | $0.4 | — | 1.0M |
| Abacus | $0.1 | $0.4 | $0.025 | 1.0M |
| Cloudflare AI Gateway | $0.1 | $0.4 | $0.025 | 1.0M |
| Eden AI | $0.1 | $0.4 | $0.025 | 1.0M |
| Impossibl | $0.1 | $0.4 | $0.025 | 1.0M |
| Kilo Gateway | $0.1 | $0.4 | $0.025 | 1.0M |
| DevPass (LLM Gateway) | $0.1 | $0.4 | $0.025 | 1.0M |
| LLM Gateway | $0.1 | $0.4 | $0.025 | 1.0M |
| LLM Gateway | $0.1 | $0.4 | $0.025 | 1.0M |
| Merge Gateway | $0.1 | $0.4 | $0.025 | 1.0M |
| NanoGPT | $0.1 | $0.4 | $0.025 | 1.0M |
| NEAR AI Cloud | $0.1 | $0.4 | $0.025 | 1.0M |
| OpenRouter | $0.1 | $0.4 | $0.025 | 1.0M |
| OrcaRouter | $0.1 | $0.4 | $0.025 | 1.0M |
| Pioneer | $0.1 | $0.4 | $0.05 | 1.0M |
| Cortecs | $0.111 | $0.434 | $0.056 | 1.0M |
| Requesty (eu) | $0.11 | $0.44 | $0.0275 | 1.0M |

## Summary

- Cheapest input: $0.08 per 1M tokens (SAP AI Core)
- Cheapest output: $0.26 per 1M tokens (SAP AI Core)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-04-14
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-4.1 nano API?

As of Oct 4, 2026, SAP AI Core has the lowest GPT-4.1 nano output price at $0.26 per 1M tokens, and SAP AI Core has the lowest input price at $0.08 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer GPT-4.1 nano?

19 providers list GPT-4.1 nano on Sovyron; 20 of them sell it at a metered per-token price.

### Is GPT-4.1 nano free?

No provider in the Sovyron catalog lists a free tier for GPT-4.1 nano.

### What is the context window of GPT-4.1 nano?

GPT-4.1 nano supports a 1.0M-token context window and up to 33k output tokens.

HTML page: https://sovyron.com/models/gpt-4-1-nano/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.1 Codex API prices

GPT-5.1 Codex (gpt-codex) — 400k context, 272k max output.
19 metered per-token offers from 19 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| OpenCode Zen | $1.07 | $8.5 | $0.107 | 400k |
| Poe | $1.1 | $9 | $0.11 | 400k |
| Jiekou.AI | $1.125 | $9 | — | 400k |
| Abacus | $1.25 | $10 | $0.125 | 400k |
| AIHubMix | $1.25 | $10 | $0.125 | 400k |
| Azure | $1.25 | $10 | $0.125 | 400k |
| Azure Cognitive Services | $1.25 | $10 | $0.125 | 400k |
| Eden AI | $1.25 | $10 | $0.125 | 272k |
| Helicone | $1.25 | $10 | $0.125 | 400k |
| Impossibl | $1.25 | $10 | $0.125 | 400k |
| Kilo Gateway | $1.25 | $10 | $0.13 | 400k |
| DevPass (LLM Gateway) | $1.25 | $10 | $0.125 | 400k |
| LLM Gateway | $1.25 | $10 | — | 400k |
| NanoGPT | $1.25 | $10 | $0.125 | 400k |
| OpenRouter | $1.25 | $10 | $0.13 | 400k |
| OrcaRouter | $1.25 | $10 | $0.125 | 400k |
| Vercel AI Gateway | $1.25 | $10 | $0.13 | 400k |
| Vivgrid | $1.25 | $10 | $0.125 | 400k |
| ZenMux | $1.25 | $10 | $0.12 | 400k |

## Summary

- Cheapest input: $1.07 per 1M tokens (OpenCode Zen)
- Cheapest output: $8.5 per 1M tokens (OpenCode Zen)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-11-13
- Inputs: audio, image, pdf, text

## FAQ

### What is the cheapest GPT-5.1 Codex API?

As of Oct 4, 2026, OpenCode Zen has the lowest GPT-5.1 Codex output price at $8.5 per 1M tokens, and OpenCode Zen has the lowest input price at $1.07 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer GPT-5.1 Codex?

19 providers list GPT-5.1 Codex on Sovyron; 19 of them sell it at a metered per-token price.

### Is GPT-5.1 Codex free?

No provider in the Sovyron catalog lists a free tier for GPT-5.1 Codex.

### What is the context window of GPT-5.1 Codex?

GPT-5.1 Codex supports a 400k-token context window and up to 272k output tokens.

HTML page: https://sovyron.com/models/gpt-5-1-codex/
Full dataset: https://sovyron.com/data/catalog.json

---

# Grok Build 0.1 API prices

Grok Build 0.1 (grok-build) — 256k context, 256k max output.
19 metered per-token offers from 20 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| AIHubMix | $1 | $2 | $0.2 | 256k |
| CrossModel | $1 | $2 | $0.2 | 256k |
| Eden AI | $1 | $2 | $0.2 | 256k |
| FastRouter | $1 | $2 | — | 256k |
| Impossibl | $1 | $2 | $0.2 | 256k |
| Kilo Gateway | $1 | $2 | $0.2 | 256k |
| DevPass (LLM Gateway) | $1 | $2 | $0.2 | 256k |
| LLM Gateway | $1 | $2 | $0.2 | 256k |
| Merge Gateway | $1 | $2 | $0.2 | 256k |
| NanoGPT | $1 | $2 | $0.2 | 256k |
| OpenCode Zen | $1 | $2 | $0.2 | 256k |
| OpenRouter | $1 | $2 | $0.2 | 256k |
| Opper | $1 | $2 | $0.2 | 256k |
| Requesty | $1 | $2 | $0.1 | 256k |
| Tempr Gateway | $1 | $2 | $0.2 | 256k |
| Venice AI | $1 | $2 | $0.2 | 256k |
| Vercel AI Gateway | $1 | $2 | $0.2 | 256k |
| xAI | $1 | $2 | $0.2 | 256k |
| ZenMux | $1 | $2 | $0.2 | 256k |

## Summary

- Cheapest input: $1 per 1M tokens (AIHubMix)
- Cheapest output: $2 per 1M tokens (AIHubMix)
- First-party: $2 per 1M output tokens (xAI)
- Free offers: Kenari
- Subscription plans (not per-token): none
- Released: 2026-04-16
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Grok Build 0.1 API?

As of Oct 4, 2026, AIHubMix has the lowest Grok Build 0.1 output price at $2 per 1M tokens, and AIHubMix has the lowest input price at $1 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Grok Build 0.1 cost on xAI?

xAI charges $1 per 1M input tokens and $2 per 1M output tokens for Grok Build 0.1.

### How many providers offer Grok Build 0.1?

20 providers list Grok Build 0.1 on Sovyron; 19 of them sell it at a metered per-token price.

### Is Grok Build 0.1 free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### What is the context window of Grok Build 0.1?

Grok Build 0.1 supports a 256k-token context window and up to 256k output tokens.

HTML page: https://sovyron.com/models/grok-build-0-1/
Full dataset: https://sovyron.com/data/catalog.json

---

# MiMo-V2.5-Pro API prices

MiMo-V2.5-Pro (mimo) — 1.1M context, 262k max output.
21 metered per-token offers from 24 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| CrofAI | $0.4 | $0.8 | $0.003 | 1.0M |
| Kilo Gateway | $0.435 | $0.87 | $0.004 | 1.0M |
| DevPass (LLM Gateway) | $0.435 | $0.87 | $0.0036 | 1.0M |
| LLM Gateway | $0.435 | $0.87 | $0.0036 | 1.0M |
| LLM Gateway | $0.435 | $0.87 | $0.0036 | 1.0M |
| LLMTR | $0.435 | $0.87 | — | 1.0M |
| NanoGPT | $0.435 | $0.87 | $0.0036 | 1.0M |
| OpenCode Go | $0.435 | $0.87 | $0.0036 | 1.0M |
| OpenRouter | $0.435 | $0.87 | $0.0036 | 1.1M |
| Pioneer | $0.435 | $0.87 | $0.0036 | 1.1M |
| Requesty | $0.435 | $0.87 | $0.0036 | 1.0M |
| Vercel AI Gateway | $0.435 | $0.87 | $0.0036 | 1.1M |
| Xiaomi | $0.435 | $0.87 | $0.0036 | 1.0M |
| CrossModel | $0.47 | $0.94 | $0.005 | 1.0M |
| AIHubMix | $0.48 | $0.96 | $0.0038 | 1.0M |
| LLM Gateway | $0.522 | $1.044 | $0.0043 | 1.0M |
| NovitaAI | $0.522 | $1.044 | $0.0043 | 1.0M |
| DigitalOcean | $0.8 | $3 | $0.16 | 262k |
| Hugging Face | $1 | $3 | — | 1.0M |
| ZenMux | $1 | $3 | $0.2 | 1.0M |
| EmpirioLabs AI | $2.175 | $4.35 | $0.018 | 1.0M |

## Summary

- Cheapest input: $0.4 per 1M tokens (CrofAI)
- Cheapest output: $0.8 per 1M tokens (CrofAI)
- First-party: not listed separately
- Free offers: Kenari, Xiaomi Token Plan (Europe), Xiaomi Token Plan (China), Xiaomi Token Plan (Singapore)
- Subscription plans (not per-token): ClinePass, Xiaomi Token Plan (Europe), Xiaomi Token Plan (China), Xiaomi Token Plan (Singapore)
- Released: 2026-04-22
- Inputs: text

## FAQ

### What is the cheapest MiMo-V2.5-Pro API?

As of Oct 4, 2026, CrofAI has the lowest MiMo-V2.5-Pro output price at $0.8 per 1M tokens, and CrofAI has the lowest input price at $0.4 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer MiMo-V2.5-Pro?

24 providers list MiMo-V2.5-Pro on Sovyron; 21 of them sell it at a metered per-token price.

### Is MiMo-V2.5-Pro free?

1 provider(s) list a free-tier offer: Kenari. Free tiers usually have rate limits.

### Is MiMo-V2.5-Pro included in a subscription plan?

Yes. 1 flat-rate plan(s) include it; the cheapest is OpenCode OpenCode Go at $10/month.

### What is the context window of MiMo-V2.5-Pro?

MiMo-V2.5-Pro supports a 1.1M-token context window and up to 262k output tokens.

HTML page: https://sovyron.com/models/mimo-v2-5-pro/
Full dataset: https://sovyron.com/data/catalog.json

---

# Qwen3 235B A22B Instruct 2507 API prices

Qwen3 235B A22B Instruct 2507 (qwen) — 262k context, 262k max output.
21 metered per-token offers from 21 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| OpenRouter | $0.0875 | $0.35 | $0.0175 | 262k |
| Cortecs | $0.069 | $0.455 | $0.018 | 262k |
| Deep Infra | $0.09 | $0.55 | — | 262k |
| LLM Gateway | $0.09 | $0.58 | — | 131k |
| NovitaAI | $0.09 | $0.58 | — | 131k |
| Meganova | $0.09 | $0.6 | — | 262k |
| Merge Gateway | $0.1 | $0.6 | $0.0574 | 131k |
| submodel | $0.2 | $0.3 | — | 262k |
| Nebius Token Factory | $0.2 | $0.6 | — | 262k |
| Jiekou.AI | $0.15 | $0.8 | — | 131k |
| Crusoe | $0.22 | $0.8 | $0.11 | 262k |
| Amazon Bedrock | $0.22 | $0.88 | — | 262k |
| LLM Gateway | $0.22 | $0.88 | — | 262k |
| Vercel AI Gateway | $0.22 | $0.88 | — | 262k |
| Eden AI | $0.23 | $0.92 | — | 131k |
| 302.AI | $0.29 | $1.143 | — | 128k |
| LLM Gateway | $0.6 | $1.2 | — | 262k |
| Scaleway | $0.75 | $2.25 | — | 260k |
| Pioneer | $1.2 | $1.2 | $1.2 | 262k |
| Hugging Face | $0.855 | $2.565 | — | 262k |
| GreenPT | $1.026 | $3.078 | — | 262k |

## Summary

- Cheapest input: $0.069 per 1M tokens (Cortecs)
- Cheapest output: $0.3 per 1M tokens (submodel)
- First-party: not listed separately
- Free offers: ModelScope
- Subscription plans (not per-token): none
- Released: 2025-07-21
- Inputs: text

## FAQ

### What is the cheapest Qwen3 235B A22B Instruct 2507 API?

As of Oct 4, 2026, submodel has the lowest Qwen3 235B A22B Instruct 2507 output price at $0.3 per 1M tokens, and Cortecs has the lowest input price at $0.069 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Qwen3 235B A22B Instruct 2507?

21 providers list Qwen3 235B A22B Instruct 2507 on Sovyron; 21 of them sell it at a metered per-token price.

### Is Qwen3 235B A22B Instruct 2507 free?

1 provider(s) list a free-tier offer: ModelScope. Free tiers usually have rate limits.

### What is the context window of Qwen3 235B A22B Instruct 2507?

Qwen3 235B A22B Instruct 2507 supports a 262k-token context window and up to 262k output tokens.

HTML page: https://sovyron.com/models/qwen3-235b-a22b-instruct-2507/
Full dataset: https://sovyron.com/data/catalog.json

---

# Qwen3 Max API prices

Qwen3 Max (qwen) — 262k context, 66k max output.
23 metered per-token offers from 23 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $0.36 | $1.43 | $0.072 | 262k |
| Ofox | $0.36 | $1.43 | $0.072 | 256k |
| Alibaba (China) | $0.359 | $1.434 | — | 262k |
| Merge Gateway | $0.359 | $1.434 | $0.0718 | 262k |
| OrcaRouter | $0.359 | $1.434 | — | 262k |
| AIHubMix | $0.4508 | $2.7048 | $0.0902 | 262k |
| DevPass (LLM Gateway) | $0.845 | $3.38 | $0.6 | 262k |
| LLM Gateway | $0.845 | $3.38 | — | 262k |
| Kilo Gateway | $0.78 | $3.9 | $0.156 | 262k |
| OpenRouter | $0.78 | $3.9 | $0.156 | 262k |
| EmpirioLabs AI | $1.08 | $5.52 | $1.08 | 256k |
| Abacus | $1.2 | $6 | — | 131k |
| Alibaba | $1.2 | $6 | — | 262k |
| Cloudflare AI Gateway | $1.2 | $6 | — | 262k |
| Deep Infra | $1.2 | $6 | $0.24 | 256k |
| Eden AI | $1.2 | $6 | $0.24 | 262k |
| Eden AI (eu) | $1.2 | $6 | $0.24 | 262k |
| LLM Gateway | $1.2 | $6 | $0.24 | 256k |
| LLMTR | $1.2 | $6 | — | 256k |
| Vercel AI Gateway | $1.2 | $6 | $0.24 | 262k |
| Vercel AI Gateway | $1.2 | $6 | $0.24 | 262k |
| NanoGPT | $1.2002 | $6.001 | $0.6001 | 256k |
| NovitaAI | $2.11 | $8.45 | — | 262k |

## Summary

- Cheapest input: $0.359 per 1M tokens (Alibaba (China))
- Cheapest output: $1.43 per 1M tokens (Ofox)
- First-party: $6 per 1M output tokens (Alibaba)
- Free offers: Alibaba Coding Plan, Alibaba Coding Plan (China), iFlow, iFlow
- Subscription plans (not per-token): Alibaba Coding Plan, Alibaba Coding Plan (China)
- Released: 2025-09-23
- Inputs: text

## FAQ

### What is the cheapest Qwen3 Max API?

As of Oct 4, 2026, Ofox has the lowest Qwen3 Max output price at $1.43 per 1M tokens, and Alibaba (China) has the lowest input price at $0.359 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Qwen3 Max cost on Alibaba?

Alibaba charges $1.2 per 1M input tokens and $6 per 1M output tokens for Qwen3 Max.

### How many providers offer Qwen3 Max?

23 providers list Qwen3 Max on Sovyron; 23 of them sell it at a metered per-token price.

### Is Qwen3 Max free?

2 provider(s) list a free-tier offer: iFlow, iFlow. Free tiers usually have rate limits.

### What is the context window of Qwen3 Max?

Qwen3 Max supports a 262k-token context window and up to 66k output tokens.

HTML page: https://sovyron.com/models/qwen3-max/
Full dataset: https://sovyron.com/data/catalog.json

---

# Qwen3.5 122B-A10B API prices

Qwen3.5 122B-A10B (qwen) — 262k context, 262k max output.
21 metered per-token offers from 19 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| AIHubMix | $0.1126 | $0.9008 | — | 262k |
| EmpirioLabs AI | $0.115 | $0.917 | $0.115 | 256k |
| Merge Gateway | $0.115 | $0.917 | $0.023 | 131k |
| OrcaRouter | $0.115 | $0.917 | — | 262k |
| Kilo Gateway | $0.26 | $2.08 | — | 262k |
| Neon | $0.22 | $2.2 | — | 262k |
| OpenRouter | $0.26 | $2.08 | — | 262k |
| SiliconFlow | $0.26 | $2.08 | — | 262k |
| Ofox | $0.29 | $2.29 | $0.29 | 256k |
| Ofox | $0.29 | $2.29 | $0.29 | 256k |
| Alibaba | $0.4 | $3.2 | — | 262k |
| Hugging Face | $0.4 | $3.2 | — | 262k |
| Jalapeno Cloud | $0.4 | $3.2 | — | 262k |
| DevPass (LLM Gateway) | $0.4 | $3.2 | — | 262k |
| LLM Gateway | $0.4 | $3.2 | — | 262k |
| LLM Gateway | $0.4 | $3.2 | — | 262k |
| Mixlayer | $0.4 | $3.2 | — | 262k |
| NovitaAI | $0.4 | $3.2 | — | 262k |
| NanoGPT | $0.437 | $3.496 | $0.1038 | 131k |
| Cortecs | $0.495 | $3.46 | $0.124 | 262k |
| TensorX | $0.5 | $3.5 | $0.125 | 262k |

## Summary

- Cheapest input: $0.1126 per 1M tokens (AIHubMix)
- Cheapest output: $0.9008 per 1M tokens (AIHubMix)
- First-party: $3.2 per 1M output tokens (Alibaba)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-02-23
- Inputs: audio, image, text, video

## FAQ

### What is the cheapest Qwen3.5 122B-A10B API?

As of Oct 4, 2026, AIHubMix has the lowest Qwen3.5 122B-A10B output price at $0.9008 per 1M tokens, and AIHubMix has the lowest input price at $0.1126 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Qwen3.5 122B-A10B cost on Alibaba?

Alibaba charges $0.4 per 1M input tokens and $3.2 per 1M output tokens for Qwen3.5 122B-A10B.

### How many providers offer Qwen3.5 122B-A10B?

19 providers list Qwen3.5 122B-A10B on Sovyron; 21 of them sell it at a metered per-token price.

### Is Qwen3.5 122B-A10B free?

No provider in the Sovyron catalog lists a free tier for Qwen3.5 122B-A10B.

### What is the context window of Qwen3.5 122B-A10B?

Qwen3.5 122B-A10B supports a 262k-token context window and up to 262k output tokens.

HTML page: https://sovyron.com/models/qwen3-5-122b-a10b/
Full dataset: https://sovyron.com/data/catalog.json

---

# Qwen3.5 35B-A3B API prices

Qwen3.5 35B-A3B (qwen) — 262k context, 262k max output.
20 metered per-token offers from 19 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| AIHubMix | $0.0564 | $0.4512 | — | 262k |
| EmpirioLabs AI | $0.057 | $0.459 | $0.057 | 256k |
| Merge Gateway | $0.057 | $0.459 | $0.0204 | 131k |
| OrcaRouter | $0.057 | $0.459 | — | 262k |
| 302.AI | $0.06 | $0.46 | — | 262k |
| Requesty | $0.14 | $1 | $0.05 | 262k |
| OpenRouter | $0.15 | $1 | $0.05 | 262k |
| Kilo Gateway | $0.1625 | $1.3 | — | 262k |
| CoreWeave | $0.25 | $1.25 | $0.25 | 262k |
| Mixlayer | $0.25 | $1.3 | — | 262k |
| NanoGPT | $0.225 | $1.8 | $0.1125 | 260k |
| SiliconFlow | $0.24 | $1.8 | — | 262k |
| Ofox | $0.29 | $1.83 | $0.29 | 262k |
| Ofox | $0.29 | $1.83 | $0.29 | 256k |
| Alibaba | $0.25 | $2 | — | 262k |
| Hugging Face | $0.25 | $2 | — | 262k |
| Jalapeno Cloud | $0.25 | $2 | — | 262k |
| DevPass (LLM Gateway) | $0.25 | $2 | — | 262k |
| LLM Gateway | $0.25 | $2 | — | 262k |
| NovitaAI | $0.25 | $2 | — | 262k |

## Summary

- Cheapest input: $0.0564 per 1M tokens (AIHubMix)
- Cheapest output: $0.4512 per 1M tokens (AIHubMix)
- First-party: $2 per 1M output tokens (Alibaba)
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-02-23
- Inputs: audio, image, text, video

## FAQ

### What is the cheapest Qwen3.5 35B-A3B API?

As of Oct 4, 2026, AIHubMix has the lowest Qwen3.5 35B-A3B output price at $0.4512 per 1M tokens, and AIHubMix has the lowest input price at $0.0564 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does Qwen3.5 35B-A3B cost on Alibaba?

Alibaba charges $0.25 per 1M input tokens and $2 per 1M output tokens for Qwen3.5 35B-A3B.

### How many providers offer Qwen3.5 35B-A3B?

19 providers list Qwen3.5 35B-A3B on Sovyron; 20 of them sell it at a metered per-token price.

### Is Qwen3.5 35B-A3B free?

No provider in the Sovyron catalog lists a free tier for Qwen3.5 35B-A3B.

### What is the context window of Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B supports a 262k-token context window and up to 262k output tokens.

HTML page: https://sovyron.com/models/qwen3-5-35b-a3b/
Full dataset: https://sovyron.com/data/catalog.json

---

# Claude Opus 4.1 API prices

Claude Opus 4.1 (claude-opus) — 200k context, 64k max output.
19 metered per-token offers from 19 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Poe | $13 | $64 | $1.3 | 197k |
| Abacus | $15 | $75 | — | 200k |
| Azure | $15 | $75 | $1.5 | 200k |
| Azure Cognitive Services | $15 | $75 | $1.5 | 200k |
| Databricks | $15 | $75 | $1.5 | 200k |
| DigitalOcean | $15 | $75 | $1.5 | 200k |
| FastRouter | $15 | $75 | $1.5 | 200k |
| Helicone | $15 | $75 | $1.5 | 200k |
| Helicone | $15 | $75 | $1.5 | 200k |
| Kilo Gateway | $15 | $75 | $1.5 | 200k |
| DevPass (LLM Gateway) | $15 | $75 | $1.5 | 200k |
| LLM Gateway | $15 | $75 | $1.5 | 200k |
| Merge Gateway | $15 | $75 | $1.5 | 200k |
| NanoGPT | $15 | $75 | $1.5 | 200k |
| Neon | $15 | $75 | $1.5 | 200k |
| OpenRouter | $15 | $75 | $1.5 | 200k |
| Pioneer | $15 | $75 | $1.5 | 200k |
| Requesty | $15 | $75 | $1.5 | 200k |
| ZenMux | $15 | $75 | $1.5 | 200k |

## Summary

- Cheapest input: $13 per 1M tokens (Poe)
- Cheapest output: $64 per 1M tokens (Poe)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-08-05
- Inputs: image, pdf, text

## FAQ

### What is the cheapest Claude Opus 4.1 API?

As of Oct 4, 2026, Poe has the lowest Claude Opus 4.1 output price at $64 per 1M tokens, and Poe has the lowest input price at $13 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Claude Opus 4.1?

19 providers list Claude Opus 4.1 on Sovyron; 19 of them sell it at a metered per-token price.

### Is Claude Opus 4.1 free?

No provider in the Sovyron catalog lists a free tier for Claude Opus 4.1.

### What is the context window of Claude Opus 4.1?

Claude Opus 4.1 supports a 200k-token context window and up to 64k output tokens.

HTML page: https://sovyron.com/models/claude-opus-4-1/
Full dataset: https://sovyron.com/data/catalog.json

---

# GLM-4.5 API prices

GLM-4.5 (glm) — 131k context, 98k max output.
19 metered per-token offers from 20 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| 302.AI | $0.286 | $1.142 | — | 131k |
| ZenMux | $0.2911 | $1.1645 | $0.0582 | 128k |
| NanoGPT | $0.3 | $1.3 | $0.15 | 128k |
| NanoGPT | $0.3 | $1.3 | $0.15 | 128k |
| Abacus | $0.6 | $2.2 | — | 131k |
| Hugging Face | $0.6 | $2.2 | — | 131k |
| Impossibl | $0.6 | $2.2 | $0.11 | 131k |
| Jiekou.AI | $0.6 | $2.2 | — | 131k |
| Kilo Gateway | $0.6 | $2.2 | $0.11 | 131k |
| DevPass (LLM Gateway) | $0.6 | $2.2 | $0.11 | 131k |
| LLM Gateway | $0.6 | $2.2 | $0.11 | 128k |
| Merge Gateway | $0.6 | $2.2 | $0.11 | 128k |
| NovitaAI | $0.6 | $2.2 | $0.11 | 131k |
| OpenRouter | $0.6 | $2.2 | $0.11 | 131k |
| OrcaRouter | $0.6 | $2.2 | $0.11 | 131k |
| Tempr Gateway | $0.6 | $2.2 | $0.11 | 131k |
| Vercel AI Gateway | $0.6 | $2.2 | $0.11 | 128k |
| Z.AI | $0.6 | $2.2 | $0.11 | 131k |
| Zhipu AI | $0.6 | $2.2 | $0.11 | 131k |

## Summary

- Cheapest input: $0.286 per 1M tokens (302.AI)
- Cheapest output: $1.142 per 1M tokens (302.AI)
- First-party: $2.2 per 1M output tokens (Z.AI)
- Free offers: ModelScope
- Subscription plans (not per-token): none
- Released: 2025-07-28
- Inputs: text

## FAQ

### What is the cheapest GLM-4.5 API?

As of Oct 4, 2026, 302.AI has the lowest GLM-4.5 output price at $1.142 per 1M tokens, and 302.AI has the lowest input price at $0.286 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GLM-4.5 cost on Z.AI?

Z.AI charges $0.6 per 1M input tokens and $2.2 per 1M output tokens for GLM-4.5.

### How many providers offer GLM-4.5?

20 providers list GLM-4.5 on Sovyron; 19 of them sell it at a metered per-token price.

### Is GLM-4.5 free?

1 provider(s) list a free-tier offer: ModelScope. Free tiers usually have rate limits.

### What is the context window of GLM-4.5?

GLM-4.5 supports a 131k-token context window and up to 98k output tokens.

HTML page: https://sovyron.com/models/glm-4-5/
Full dataset: https://sovyron.com/data/catalog.json

---

# GLM-5-Turbo API prices

GLM-5-Turbo (glm) — 203k context, 203k max output.
18 metered per-token offers from 19 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| 302.AI | $0.72 | $3.2 | — | 200k |
| ZenMux | $0.73 | $3.19 | $0.174 | 200k |
| CrossModel | $0.9 | $3.7 | $0.18 | 200k |
| Cortecs | $1.186 | $3.955 | $0.296 | 203k |
| Eden AI | $1.2 | $4 | $0.24 | 203k |
| Impossibl | $1.2 | $4 | $0.24 | 200k |
| Kilo Gateway | $1.2 | $4 | $0.24 | 203k |
| DevPass (LLM Gateway) | $1.2 | $4 | $0.24 | 200k |
| LLM Gateway | $1.2 | $4 | $0.24 | 200k |
| Merge Gateway | $1.2 | $4 | $0.24 | 200k |
| NanoGPT | $1.2 | $4 | $0.24 | 203k |
| Ofox | $1.2 | $4 | $0.24 | 200k |
| OpenRouter | $1.2 | $4 | $0.24 | 203k |
| Tempr Gateway | $1.2 | $4 | $0.24 | 200k |
| TensorX | $1.2 | $4 | $0.3 | 203k |
| Venice AI | $1.2 | $4 | $0.24 | 200k |
| Vercel AI Gateway | $1.2 | $4 | $0.24 | 203k |
| Z.AI | $1.2 | $4 | $0.24 | 200k |

## Summary

- Cheapest input: $0.72 per 1M tokens (302.AI)
- Cheapest output: $3.19 per 1M tokens (ZenMux)
- First-party: $4 per 1M output tokens (Z.AI)
- Free offers: Z.AI Coding Plan
- Subscription plans (not per-token): Z.AI Coding Plan
- Released: 2026-03-16
- Inputs: text

## FAQ

### What is the cheapest GLM-5-Turbo API?

As of Oct 4, 2026, ZenMux has the lowest GLM-5-Turbo output price at $3.19 per 1M tokens, and 302.AI has the lowest input price at $0.72 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How much does GLM-5-Turbo cost on Z.AI?

Z.AI charges $1.2 per 1M input tokens and $4 per 1M output tokens for GLM-5-Turbo.

### How many providers offer GLM-5-Turbo?

19 providers list GLM-5-Turbo on Sovyron; 18 of them sell it at a metered per-token price.

### Is GLM-5-Turbo free?

No provider in the Sovyron catalog lists a free tier for GLM-5-Turbo.

### Is GLM-5-Turbo included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is Z.ai GLM Coding Lite at $18/month.

### What is the context window of GLM-5-Turbo?

GLM-5-Turbo supports a 203k-token context window and up to 203k output tokens.

HTML page: https://sovyron.com/models/glm-5-turbo/
Full dataset: https://sovyron.com/data/catalog.json

---

# GPT-5.1 Codex mini API prices

GPT-5.1 Codex mini (gpt-codex) — 400k context, 128k max output.
18 metered per-token offers from 18 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Ofox | $0.2 | $1.6 | $0.024 | 256k |
| Poe | $0.22 | $1.8 | $0.022 | 400k |
| Jiekou.AI | $0.225 | $1.8 | — | 400k |
| AIHubMix | $0.25 | $2 | $0.025 | 400k |
| Azure | $0.25 | $2 | $0.025 | 400k |
| Azure Cognitive Services | $0.25 | $2 | $0.025 | 400k |
| Eden AI | $0.25 | $2 | $0.025 | 272k |
| Helicone | $0.25 | $2 | $0.025 | 400k |
| Impossibl | $0.25 | $2 | $0.025 | 400k |
| Kilo Gateway | $0.25 | $2 | $0.03 | 400k |
| DevPass (LLM Gateway) | $0.25 | $2 | $0.025 | 400k |
| LLM Gateway | $0.25 | $2 | $0.025 | 400k |
| NanoGPT | $0.25 | $2 | $0.025 | 400k |
| OpenCode Zen | $0.25 | $2 | $0.025 | 400k |
| OpenRouter | $0.25 | $2 | $0.03 | 400k |
| OrcaRouter | $0.25 | $2 | $0.025 | 400k |
| Vercel AI Gateway | $0.25 | $2 | $0.03 | 400k |
| ZenMux | $0.25 | $2 | $0.03 | 400k |

## Summary

- Cheapest input: $0.2 per 1M tokens (Ofox)
- Cheapest output: $1.6 per 1M tokens (Ofox)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-11-13
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5.1 Codex mini API?

As of Oct 4, 2026, Ofox has the lowest GPT-5.1 Codex mini output price at $1.6 per 1M tokens, and Ofox has the lowest input price at $0.2 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer GPT-5.1 Codex mini?

18 providers list GPT-5.1 Codex mini on Sovyron; 18 of them sell it at a metered per-token price.

### Is GPT-5.1 Codex mini free?

No provider in the Sovyron catalog lists a free tier for GPT-5.1 Codex mini.

### What is the context window of GPT-5.1 Codex mini?

GPT-5.1 Codex mini supports a 400k-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-1-codex-mini/
Full dataset: https://sovyron.com/data/catalog.json


Truncated at 100 of 149 models. Full dataset: https://sovyron.com/data/catalog.json