# 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