# Sovyron

> Per-token price comparison for 1985 canonical LLM models across 226 providers, normalized from the models.dev catalog. Prices are USD per 1M tokens; data last refreshed 2026-10-04.

Cite as: Sovyron (https://sovyron.com/), prices as of 2026-10-04.

Cheapest input/output figures ignore free tiers and subscription plans, so every number is a real metered per-token rate.
Model, provider and plan pages are also served as Markdown: append `.md` to the page URL without the trailing slash (e.g. /models/<slug>.md, /providers/<id>.md, /plans/<slug>.md).

## Data

- [catalog.json](https://sovyron.com/data/catalog.json): full dataset — every canonical model with every provider offer, context tiers and free/plan flags
- [matrix.json](https://sovyron.com/data/matrix.json): pinned providers × popular models, the payload the /matrix/ page renders
- [Methodology](https://sovyron.com/methodology/): sources, normalization, cheapest-offer rules, update schedule
- [llms-full.txt](https://sovyron.com/llms-full.txt): every popular model's price table in one Markdown file
- [sitemap](https://sovyron.com/sitemap-index.xml): every page URL
- [llms.txt](https://sovyron.com/llms.txt): this file

## Quick answers

- Cheapest GLM-5.3-Flash output: $0.025 per 1M tokens (TokenGo) — https://sovyron.com/models/glm-5-3-flash/
- Cheapest Llama 3.1 8B Instruct output: $0.025 per 1M tokens (Inference) — https://sovyron.com/models/llama-3-1-8b-instruct/
- Cheapest DeepSeek V4 Flash output: $0.07 per 1M tokens (Merge Gateway) — https://sovyron.com/models/deepseek-v4-flash/
- Cheapest DeepSeek V4 Flash 0731 output: $0.07 per 1M tokens (Merge Gateway) — https://sovyron.com/models/deepseek-v4-flash-0731/
- Cheapest DeepSeek V4.1 Flash output: $0.08 per 1M tokens (engy) — https://sovyron.com/models/deepseek-v4-1-flash/

## Popular models

- [GLM-5.2](https://sovyron.com/models/glm-5-2/): $0.064 in / $1.05 out per 1M tokens, 84 providers
- [Kimi K3](https://sovyron.com/models/kimi-k3/): $0.72 in / $8 out per 1M tokens, 75 providers
- [GLM-5.3-Flash](https://sovyron.com/models/glm-5-3-flash/): $0.03 in / $0.025 out per 1M tokens, 69 providers
- [GPT OSS 120B](https://sovyron.com/models/gpt-oss-120b/): $0.03 in / $0.1 out per 1M tokens, 61 providers
- [Kimi K2.6](https://sovyron.com/models/kimi-k2-6/): $0.275 in / $1.1 out per 1M tokens, 62 providers
- [GLM-5.3](https://sovyron.com/models/glm-5-3/): $0.4 in / $1.4 out per 1M tokens, 69 providers
- [DeepSeek V4 Pro](https://sovyron.com/models/deepseek-v4-pro/): $0.2088 in / $0.4176 out per 1M tokens, 63 providers
- [Kimi K2.7 Code](https://sovyron.com/models/kimi-k2-7-code/): $0.275 in / $1.1 out per 1M tokens, 57 providers
- [DeepSeek V4 Flash](https://sovyron.com/models/deepseek-v4-flash/): $0.0152 in / $0.07 out per 1M tokens, 60 providers
- [DeepSeek V4.1 Flash](https://sovyron.com/models/deepseek-v4-1-flash/): $0.003 in / $0.08 out per 1M tokens, 55 providers
- [GLM-5.1](https://sovyron.com/models/glm-5-1/): $0.45 in / $2.15 out per 1M tokens, 51 providers
- [Claude Sonnet 4.6](https://sovyron.com/models/claude-sonnet-4-6/): $0.9 in / $5.55 out per 1M tokens, 50 providers
- [MiniMax-M3](https://sovyron.com/models/minimax-m3/): $0.2 in / $0.9 out per 1M tokens, 51 providers
- [GPT-5.5](https://sovyron.com/models/gpt-5-5/): $0.1875 in / $1.125 out per 1M tokens, 47 providers
- [Claude Haiku 4.5](https://sovyron.com/models/claude-haiku-4-5/): $0.14 in / $0.71 out per 1M tokens, 47 providers
- [Claude Opus 4.7](https://sovyron.com/models/claude-opus-4-7/): $4.3 in / $21 out per 1M tokens, 46 providers
- [Claude Opus 4.8](https://sovyron.com/models/claude-opus-4-8/): $0.425 in / $2.125 out per 1M tokens, 47 providers
- [DeepSeek V4 Flash 0731](https://sovyron.com/models/deepseek-v4-flash-0731/): $0.0152 in / $0.07 out per 1M tokens, 44 providers
- [Claude Opus 4.6](https://sovyron.com/models/claude-opus-4-6/): $4.3 in / $21 out per 1M tokens, 42 providers
- [GPT-5.4](https://sovyron.com/models/gpt-5-4/): $0.75 in / $6 out per 1M tokens, 44 providers
- [Qwen3.8 27B](https://sovyron.com/models/qwen3-8-27b/): $0.045 in / $0.32 out per 1M tokens, 40 providers
- [MiniMax-M2.7](https://sovyron.com/models/minimax-m2-7/): $0.08 in / $0.32 out per 1M tokens, 41 providers
- [Claude Opus 4.5](https://sovyron.com/models/claude-opus-4-5/): $0.71 in / $3.57 out per 1M tokens, 38 providers
- [Claude Sonnet 4.5](https://sovyron.com/models/claude-sonnet-4-5/): $0.43 in / $2.14 out per 1M tokens, 39 providers
- [GLM-5](https://sovyron.com/models/glm-5/): $0.4 in / $1.75 out per 1M tokens, 43 providers
- [GPT-5.6 Luna](https://sovyron.com/models/gpt-5-6-luna/): $0.06 in / $0.37 out per 1M tokens, 39 providers
- [Kimi K2.5](https://sovyron.com/models/kimi-k2-5/): $0.3 in / $1.9 out per 1M tokens, 44 providers
- [Claude Fable 5](https://sovyron.com/models/claude-fable-5/): $3 in / $18.5 out per 1M tokens, 39 providers
- [GPT-5.4 mini](https://sovyron.com/models/gpt-5-4-mini/): $0.375 in / $3.6 out per 1M tokens, 38 providers
- [GPT-5.6 Sol](https://sovyron.com/models/gpt-5-6-sol/): $1.5 in / $10 out per 1M tokens, 39 providers
- [GPT-5.6 Terra](https://sovyron.com/models/gpt-5-6-terra/): $1.5 in / $2 out per 1M tokens, 38 providers
- [Claude Sonnet 5](https://sovyron.com/models/claude-sonnet-5/): $1.44 in / $7.2 out per 1M tokens, 38 providers
- [GPT OSS 20B](https://sovyron.com/models/gpt-oss-20b/): $0.018 in / $0.09 out per 1M tokens, 39 providers
- [GPT-5 Mini](https://sovyron.com/models/gpt-5-mini/): $0.04 in / $0.29 out per 1M tokens, 35 providers
- [GPT-5.4 nano](https://sovyron.com/models/gpt-5-4-nano/): $0.16 in / $1 out per 1M tokens, 34 providers
- [Gemini 3.5 Flash](https://sovyron.com/models/gemini-3-5-flash/): $0.1857 in / $1.1142 out per 1M tokens, 34 providers
- [Claude Opus 5](https://sovyron.com/models/claude-opus-5/): $5 in / $25 out per 1M tokens, 35 providers
- [DeepSeek V4 Pro 0813](https://sovyron.com/models/deepseek-v4-pro-0813/): $0.442 in / $0.884 out per 1M tokens, 34 providers
- [Gemini 2.5 Flash](https://sovyron.com/models/gemini-2-5-flash/): $0.09 in / $0.6 out per 1M tokens, 34 providers
- [Gemini 3.1 Pro Preview](https://sovyron.com/models/gemini-3-1-pro-preview/): $1 in / $6 out per 1M tokens, 33 providers
- [MiniMax-M2.5](https://sovyron.com/models/minimax-m2-5/): $0.1938 in / $0.88 out per 1M tokens, 41 providers
- [GPT-5](https://sovyron.com/models/gpt-5/): $1 in / $8 out per 1M tokens, 34 providers
- [GPT-5.2](https://sovyron.com/models/gpt-5-2/): $0.25 in / $2 out per 1M tokens, 33 providers
- [Gemini 2.5 Pro](https://sovyron.com/models/gemini-2-5-pro/): $0.87 in / $7 out per 1M tokens, 32 providers
- [DeepSeek V3.2](https://sovyron.com/models/deepseek-v3-2/): $0.18 in / $0.326 out per 1M tokens, 32 providers
- [GLM-4.7](https://sovyron.com/models/glm-4-7/): $0.2 in / $0.8 out per 1M tokens, 34 providers
- [GPT-5 Nano](https://sovyron.com/models/gpt-5-nano/): $0.04 in / $0.32 out per 1M tokens, 30 providers
- [GPT-5.1](https://sovyron.com/models/gpt-5-1/): $1 in / $8 out per 1M tokens, 31 providers
- [Gemini 3 Flash Preview](https://sovyron.com/models/gemini-3-flash-preview/): $0.07 in / $0.43 out per 1M tokens, 30 providers
- [Grok 4.3](https://sovyron.com/models/grok-4-3/): $1.25 in / $2.5 out per 1M tokens, 30 providers
- [Llama-3.3-70B-Instruct](https://sovyron.com/models/llama-3-3-70b-instruct/): $0.05 in / $0.23 out per 1M tokens, 33 providers
- [Claude Fable 5.1](https://sovyron.com/models/claude-fable-5-1/): $10 in / $50 out per 1M tokens, 29 providers
- [GPT-5.3 Codex](https://sovyron.com/models/gpt-5-3-codex/): $1.4 in / $11.2 out per 1M tokens, 29 providers
- [Grok 4.6](https://sovyron.com/models/grok-4-6/): $2 in / $6 out per 1M tokens, 31 providers
- [Qwen3.8 Max](https://sovyron.com/models/qwen3-8-max/): $0.338 in / $1.014 out per 1M tokens, 33 providers
- [Claude Opus 5.5](https://sovyron.com/models/claude-opus-5-5/): $4 in / $20 out per 1M tokens, 28 providers
- [Gemini 3.1 Flash Lite](https://sovyron.com/models/gemini-3-1-flash-lite/): $0.125 in / $0.75 out per 1M tokens, 28 providers
- [Qwen3.5 397B-A17B](https://sovyron.com/models/qwen3-5-397b-a17b/): $0.1644 in / $0.9864 out per 1M tokens, 28 providers
- [Qwen3.6 35B-A3B](https://sovyron.com/models/qwen3-6-35b-a3b/): $0.045 in / $0.3 out per 1M tokens, 29 providers
- [Qwen3.7 Max](https://sovyron.com/models/qwen3-7-max/): $0.825 in / $2.4755 out per 1M tokens, 29 providers
- [GLM-4.6](https://sovyron.com/models/glm-4-6/): $0.274 in / $1.0959 out per 1M tokens, 29 providers
- [GPT-6 Astra](https://sovyron.com/models/gpt-6-astra/): $8 in / $40 out per 1M tokens, 26 providers
- [Gemini 3.5 Flash Lite](https://sovyron.com/models/gemini-3-5-flash-lite/): $0.15 in / $1.25 out per 1M tokens, 26 providers
- [Grok 4.5](https://sovyron.com/models/grok-4-5/): $2 in / $6 out per 1M tokens, 27 providers
- [GPT-4.1](https://sovyron.com/models/gpt-4-1/): $1.6 in / $6.4 out per 1M tokens, 27 providers
- [GPT-6 Luna](https://sovyron.com/models/gpt-6-luna/): $0.08 in / $0.4 out per 1M tokens, 25 providers
- [GPT-6 Sol](https://sovyron.com/models/gpt-6-sol/): $1.6 in / $8 out per 1M tokens, 25 providers
- [Gemini 3.6 Flash](https://sovyron.com/models/gemini-3-6-flash/): $0.375 in / $1.875 out per 1M tokens, 26 providers
- [Gemma 4 31B IT](https://sovyron.com/models/gemma-4-31b-it/): $0.09 in / $0.25 out per 1M tokens, 32 providers
- [GPT-4.1 mini](https://sovyron.com/models/gpt-4-1-mini/): $0.32 in / $1.28 out per 1M tokens, 25 providers
- [Qwen3.7 Plus](https://sovyron.com/models/qwen3-7-plus/): $0.282 in / $1.128 out per 1M tokens, 29 providers
- [Claude Sonnet 5.5](https://sovyron.com/models/claude-sonnet-5-5/): $2 in / $10 out per 1M tokens, 23 providers
- [GPT-4o mini](https://sovyron.com/models/gpt-4o-mini/): $0.075 in / $0.3 out per 1M tokens, 22 providers
- [Gemini 2.5 Flash-Lite](https://sovyron.com/models/gemini-2-5-flash-lite/): $0.07 in / $0.1 out per 1M tokens, 25 providers
- [Gemini 3.7 Flash](https://sovyron.com/models/gemini-3-7-flash/): $0.75 in / $3.75 out per 1M tokens, 24 providers
- [Inkling](https://sovyron.com/models/inkling/): $0.95 in / $4.05 out per 1M tokens, 22 providers
- [GPT-4o](https://sovyron.com/models/gpt-4o/): $1.25 in / $5 out per 1M tokens, 22 providers
- [Gemini 3.8 Flash](https://sovyron.com/models/gemini-3-8-flash/): $0.75 in / $3.75 out per 1M tokens, 23 providers
- [Qwen3.6 27B](https://sovyron.com/models/qwen3-6-27b/): $0.2 in / $0.6 out per 1M tokens, 24 providers
- [Qwen3.8 Flash](https://sovyron.com/models/qwen3-8-flash/): $0.11 in / $0.38 out per 1M tokens, 25 providers
- [o3](https://sovyron.com/models/o3/): $1.8 in / $7.2 out per 1M tokens, 22 providers
- [GPT-5.2 Codex](https://sovyron.com/models/gpt-5-2-codex/): $0.14 in / $1.14 out per 1M tokens, 20 providers
- [GPT-5.4 Pro](https://sovyron.com/models/gpt-5-4-pro/): $24 in / $144 out per 1M tokens, 20 providers
- [GPT-5.5 Pro](https://sovyron.com/models/gpt-5-5-pro/): $27.2727 in / $163.6364 out per 1M tokens, 20 providers
- [GPT-6.1 Sol](https://sovyron.com/models/gpt-6-1-sol/): $2 in / $10 out per 1M tokens, 21 providers
- [Grok 4.7](https://sovyron.com/models/grok-4-7/): $1.6 in / $4.8 out per 1M tokens, 21 providers
- [MiniMax-M2.1](https://sovyron.com/models/minimax-m2-1/): $0.27 in / $1.1 out per 1M tokens, 24 providers
- [Qwen3.6 Plus](https://sovyron.com/models/qwen3-6-plus/): $0.276 in / $1.651 out per 1M tokens, 24 providers
- [GPT-4.1 nano](https://sovyron.com/models/gpt-4-1-nano/): $0.08 in / $0.26 out per 1M tokens, 19 providers
- [GPT-5.1 Codex](https://sovyron.com/models/gpt-5-1-codex/): $1.07 in / $8.5 out per 1M tokens, 19 providers
- [Grok Build 0.1](https://sovyron.com/models/grok-build-0-1/): $1 in / $2 out per 1M tokens, 20 providers
- [MiMo-V2.5-Pro](https://sovyron.com/models/mimo-v2-5-pro/): $0.4 in / $0.8 out per 1M tokens, 24 providers
- [Qwen3 235B A22B Instruct 2507](https://sovyron.com/models/qwen3-235b-a22b-instruct-2507/): $0.069 in / $0.3 out per 1M tokens, 21 providers
- [Qwen3 Max](https://sovyron.com/models/qwen3-max/): $0.359 in / $1.43 out per 1M tokens, 23 providers
- [Qwen3.5 122B-A10B](https://sovyron.com/models/qwen3-5-122b-a10b/): $0.1126 in / $0.9008 out per 1M tokens, 19 providers
- [Qwen3.5 35B-A3B](https://sovyron.com/models/qwen3-5-35b-a3b/): $0.0564 in / $0.4512 out per 1M tokens, 19 providers
- [Claude Opus 4.1](https://sovyron.com/models/claude-opus-4-1/): $13 in / $64 out per 1M tokens, 19 providers
- [GLM-4.5](https://sovyron.com/models/glm-4-5/): $0.286 in / $1.142 out per 1M tokens, 20 providers
- [GLM-5-Turbo](https://sovyron.com/models/glm-5-turbo/): $0.72 in / $3.19 out per 1M tokens, 19 providers
- [GPT-5.1 Codex mini](https://sovyron.com/models/gpt-5-1-codex-mini/): $0.2 in / $1.6 out per 1M tokens, 18 providers
- [MiMo-V2.5](https://sovyron.com/models/mimo-v2-5/): $0.14 in / $0.28 out per 1M tokens, 23 providers
- [Qwen3-Next 80B-A3B Instruct](https://sovyron.com/models/qwen3-next-80b-a3b-instruct/): $0.09 in / $0.574 out per 1M tokens, 19 providers
- [Qwen3.5 27B](https://sovyron.com/models/qwen3-5-27b/): $0.0846 in / $0.6768 out per 1M tokens, 18 providers
- [Qwen3.5 9B](https://sovyron.com/models/qwen3-5-9b/): $0.04 in / $0.13 out per 1M tokens, 19 providers
- [Qwen3.8 2.4T A95B](https://sovyron.com/models/qwen3-8-2-4t-a95b/): $1.95 in / $5.95 out per 1M tokens, 18 providers
- [DeepSeek V3.1](https://sovyron.com/models/deepseek-v3-1/): $0.19 in / $0.7 out per 1M tokens, 18 providers
- [Gemma 4 26B A4B IT](https://sovyron.com/models/gemma-4-26b-a4b-it/): $0.042 in / $0.22 out per 1M tokens, 20 providers
- [Hy3](https://sovyron.com/models/hy3/): $0.066 in / $0.26 out per 1M tokens, 20 providers
- [MiMo-V2.6-Flash](https://sovyron.com/models/mimo-v2-6-flash/): $0.04 in / $0.25 out per 1M tokens, 23 providers
- [MiMo-V2.6-Pro](https://sovyron.com/models/mimo-v2-6-pro/): $0.4 in / $0.8 out per 1M tokens, 21 providers
- [MiniMax-M2](https://sovyron.com/models/minimax-m2/): $0.17 in / $1 out per 1M tokens, 20 providers
- [Qwen3-Coder 30B-A3B Instruct](https://sovyron.com/models/qwen3-coder-30b-a3b-instruct/): $0.067 in / $0.245 out per 1M tokens, 19 providers
- [Qwen3.6 Flash](https://sovyron.com/models/qwen3-6-flash/): $0.165 in / $0.99 out per 1M tokens, 19 providers
- [DeepSeek V4 Flash Vision Exp](https://sovyron.com/models/deepseek-v4-flash-vision-exp/): $0.08 in / $0.2 out per 1M tokens, 16 providers
- [GLM-4.5-Air](https://sovyron.com/models/glm-4-5-air/): $0.1 in / $0.2911 out per 1M tokens, 17 providers
- [GLM-5V-Turbo](https://sovyron.com/models/glm-5v-turbo/): $0.72 in / $3.1946 out per 1M tokens, 16 providers
- [GPT-5 Pro](https://sovyron.com/models/gpt-5-pro/): $13.5 in / $108 out per 1M tokens, 16 providers
- [Kimi K2 Thinking](https://sovyron.com/models/kimi-k2-thinking/): $0.47 in / $2 out per 1M tokens, 18 providers
- [Qwen3 32B](https://sovyron.com/models/qwen3-32b/): $0.08 in / $0.28 out per 1M tokens, 18 providers
- [o4-mini](https://sovyron.com/models/o4-mini/): $0.99 in / $4 out per 1M tokens, 18 providers
- [Claude Sonnet 4](https://sovyron.com/models/claude-sonnet-4/): $2.6 in / $13 out per 1M tokens, 15 providers
- [GLM-4.5V](https://sovyron.com/models/glm-4-5v/): $0.274 in / $0.86 out per 1M tokens, 15 providers
- [Qwen3 VL 235B A22B Instruct](https://sovyron.com/models/qwen3-vl-235b-a22b-instruct/): $0.2 in / $0.88 out per 1M tokens, 15 providers
- [o3-mini](https://sovyron.com/models/o3-mini/): $0.99 in / $4 out per 1M tokens, 16 providers
- [GLM-4.7-Flash](https://sovyron.com/models/glm-4-7-flash/): $0.06 in / $0.4 out per 1M tokens, 23 providers
- [GPT-5.1 Codex Max](https://sovyron.com/models/gpt-5-1-codex-max/): $1 in / $8 out per 1M tokens, 14 providers
- [Hy4 preview](https://sovyron.com/models/hy4-preview/): $0.67 in / $2 out per 1M tokens, 15 providers
- [Llama 3.1 8B Instruct](https://sovyron.com/models/llama-3-1-8b-instruct/): $0.02 in / $0.025 out per 1M tokens, 14 providers
- [MiniMax-M2.7-highspeed](https://sovyron.com/models/minimax-m2-7-highspeed/): $0.3 in / $1.2 out per 1M tokens, 17 providers
- [Mistral Small 4](https://sovyron.com/models/mistral-small-4/): $0.15 in / $0.6 out per 1M tokens, 14 providers
- [Muse Spark 1.2](https://sovyron.com/models/muse-spark-1-2/): $1.25 in / $4.25 out per 1M tokens, 14 providers
- [Qwen3 Coder 480B A35B Instruct](https://sovyron.com/models/qwen3-coder-480b-a35b-instruct/): $0.2 in / $0.8 out per 1M tokens, 15 providers
- [Qwen3 Coder Next](https://sovyron.com/models/qwen3-coder-next/): $0.108 in / $0.675 out per 1M tokens, 16 providers
- [Step 3.7 Flash](https://sovyron.com/models/step-3-7-flash/): $0.185 in / $1.11 out per 1M tokens, 18 providers
- [DeepSeek-R1](https://sovyron.com/models/deepseek-r1/): $0.4 in / $1.7 out per 1M tokens, 16 providers
- [GLM-4.6V](https://sovyron.com/models/glm-4-6v/): $0.137 in / $0.411 out per 1M tokens, 15 providers
- [Mistral Large 3](https://sovyron.com/models/mistral-large-3/): $0.5 in / $1.5 out per 1M tokens, 14 providers
- [Muse Spark 1.1](https://sovyron.com/models/muse-spark-1-1/): $1.25 in / $4.25 out per 1M tokens, 13 providers
- [Qwen3 Coder Plus](https://sovyron.com/models/qwen3-coder-plus/): $0.574 in / $2.294 out per 1M tokens, 16 providers
- [Qwen3.5 Plus](https://sovyron.com/models/qwen3-5-plus/): $0.1096 in / $0.6576 out per 1M tokens, 15 providers
- [DeepSeek R1 0528](https://sovyron.com/models/deepseek-r1-0528/): $0.5 in / $2.15 out per 1M tokens, 13 providers
- [Gemini 3.1 Pro Preview Custom Tools](https://sovyron.com/models/gemini-3-1-pro-preview-custom-tools/): $2 in / $12 out per 1M tokens, 12 providers
- [Grok 4.20 (Non-Reasoning)](https://sovyron.com/models/grok-4-20-non-reasoning/): $1.25 in / $2.5 out per 1M tokens, 12 providers
- [Grok 4.20 (Reasoning)](https://sovyron.com/models/grok-4-20-reasoning/): $1.25 in / $2.5 out per 1M tokens, 12 providers
- [Kimi K2.7 Code Highspeed](https://sovyron.com/models/kimi-k2-7-code-highspeed/): $1.9 in / $7.999 out per 1M tokens, 12 providers
- [Mistral Medium 3.5](https://sovyron.com/models/mistral-medium-3-5/): $1.5 in / $6.9 out per 1M tokens, 14 providers
- [Qwen3 Coder Flash](https://sovyron.com/models/qwen3-coder-flash/): $0.144 in / $0.574 out per 1M tokens, 12 providers
- [Qwen3.6 Max Preview](https://sovyron.com/models/qwen3-6-max-preview/): $1.027 in / $6.162 out per 1M tokens, 12 providers
- [Qwen3.7 Flash](https://sovyron.com/models/qwen3-7-flash/): $0.0282 in / $0.1128 out per 1M tokens, 12 providers

## Providers

- [OpenRouter](https://sovyron.com/providers/openrouter/): 373 models
- [OpenCode Zen](https://sovyron.com/providers/opencode/): 80 models
- [OpenCode Go](https://sovyron.com/providers/opencode-go/): 29 models
- [OrcaRouter](https://sovyron.com/providers/orcarouter/): 110 models
- [Requesty](https://sovyron.com/providers/requesty/): 122 models
- [NanoGPT](https://sovyron.com/providers/nano-gpt/): 580 models
- [ZenMux](https://sovyron.com/providers/zenmux/): 113 models
- [Kilo Gateway](https://sovyron.com/providers/kilo/): 382 models
- [Vercel AI Gateway](https://sovyron.com/providers/vercel/): 390 models
- [All 226 providers](https://sovyron.com/providers/): model counts, plan-based flags and docs links

## Subscription plans

- [Cheapest subscription plan per model](https://sovyron.com/plans/): every model a committed plan serves, the cheapest plan fee that covers it, its effective $/1M at 1M tokens a month, and the metered API price plus break-even it competes with. Each model links to its own plan page (https://sovyron.com/plans/<model-slug>/) listing every plan that serves it, cheapest fee first

## Languages

Localized hubs (home, models, providers, plans, matrix) in 20 languages; model and provider detail pages stay English.

- [English](https://sovyron.com/): en — home, models, providers, plans, matrix
- [English (UK)](https://sovyron.com/en-gb/): en-GB — home, models, providers, plans, matrix
- [English (Australia)](https://sovyron.com/en-au/): en-AU — home, models, providers, plans, matrix
- [English (Canada)](https://sovyron.com/en-ca/): en-CA — home, models, providers, plans, matrix
- [हिन्दी](https://sovyron.com/hi/): hi — home, models, providers, plans, matrix
- [中文](https://sovyron.com/zh-cn/): zh-CN — home, models, providers, plans, matrix
- [日本語](https://sovyron.com/ja/): ja — home, models, providers, plans, matrix
- [한국어](https://sovyron.com/ko/): ko — home, models, providers, plans, matrix
- [Bahasa Indonesia](https://sovyron.com/id/): id — home, models, providers, plans, matrix
- [Tiếng Việt](https://sovyron.com/vi/): vi — home, models, providers, plans, matrix
- [Filipino](https://sovyron.com/fil/): fil — home, models, providers, plans, matrix
- [Português (Brasil)](https://sovyron.com/pt-br/): pt-BR — home, models, providers, plans, matrix
- [Español](https://sovyron.com/es/): es — home, models, providers, plans, matrix
- [Español (México)](https://sovyron.com/es-mx/): es-MX — home, models, providers, plans, matrix
- [Deutsch](https://sovyron.com/de/): de — home, models, providers, plans, matrix
- [Français](https://sovyron.com/fr/): fr — home, models, providers, plans, matrix
- [Italiano](https://sovyron.com/it/): it — home, models, providers, plans, matrix
- [Polski](https://sovyron.com/pl/): pl — home, models, providers, plans, matrix
- [Русский](https://sovyron.com/ru/): ru — home, models, providers, plans, matrix
- [Türkçe](https://sovyron.com/tr/): tr — home, models, providers, plans, matrix