GPT OSS 20B
As of Nov 22, 2026, the cheapest GPT OSS 20B API price is $0.015 per 1M input tokens (SOKKAN Router) and $0.075 per 1M output tokens (SOKKAN Router). GPT OSS 20B is offered by 42 providers in the gpt-oss family, open weights, reasoning enabled. 4 providers list it as a free-tier offer.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.
| SOKKAN Routeropenopenai/gpt-oss-20b | Cheapest$0.015 | Cheapest$0.075 | $0.008 | — | 66k | — |
| Kilo Gatewayopenopenai/gpt-oss-20b | $0.017 | $0.085 | $0.0085 | — | 131k | yesterdayout −5.6% |
| OpenRouteropenopenai/gpt-oss-20b | $0.017 | $0.085 | $0.0085 | — | 131k | yesterdayout −5.6% |
| NanoGPTopenopenai/gpt-oss-20b | $0.018 | $0.09 | $0.009 | — | 131k | 11d agoout +200% |
| CoreWeaveopenopenai/gpt-oss-20b | $0.03 | $0.13 | $0.03 | — | 131k | — |
| Deep Infraopenopenai/gpt-oss-20b | $0.03 | $0.14 | $0.015 | — | 131k | — |
| Eden AIopendeepinfra/openai/gpt-oss-20b | $0.03 | $0.14 | $0.015 | — | 131k | — |
| Vercel AI Gatewayopenopenai/gpt-oss-20b | $0.03 | $0.14 | — | — | 131k | 66d ago |
| Kenariopengpt-oss-20b | $0.036 | $0.1543 | $0.0037 | — | 131k | 5d agoout +0% |
| Merge Gatewayopenopenai/gpt-oss-20b | $0.04 | $0.15 | $0.02 | — | 128k | 50d ago |
| Powerspringopengpt-oss-20b | $0.0442 | $0.1658 | — | — | 131k | — |
| SiliconFlowopenopenai/gpt-oss-20b | $0.04 | $0.18 | — | — | 131k | — |
| Cortecsopengpt-oss-20b | $0.045 | $0.167 | — | — | 131k | — |
| Inference APIsopenopenai/gpt-oss-20b | $0.04 | $0.19 | — | — | 131k | — |
| DevPass (LLM Gateway)opengpt-oss-20b | $0.04 | $0.19 | $0.01 | — | 131k | — |
| Clarifaiopenopenai/chat-completion/models/gpt-oss-20b | $0.045 | $0.18 | — | — | 131k | — |
| Eden AIopenovhcloud/gpt-oss-20b | $0.05 | $0.18 | — | — | 131k | — |
| OVHcloud AI Endpointsopengpt-oss-20b | $0.05 | $0.18 | — | — | 131k | — |
| Heliconeopengpt-oss-20b | $0.05 | $0.2 | — | — | 131k | 31d ago |
| IO.NETopenopenai/gpt-oss-20b | $0.055 | $0.194 | $0.0275 | — | 64k | 31d ago |
| $0.07 | $0.2 | — | — | 131k | — | |
| FastRouteropenopenai/gpt-oss-20b | $0.07 | $0.25 | $0.007 | — | 131k | 31d ago |
| Amazon Bedrockopenopenai.gpt-oss-20b | $0.07 | $0.3 | — | — | 131k | — |
| Amazon Bedrockopenopenai.gpt-oss-20b-1:0 | $0.07 | $0.3 | — | — | 131k | — |
| Databricksopendatabricks-gpt-oss-20b | $0.07 | $0.3 | — | — | 131k | 31d ago |
| Eden AIopendatabricks/databricks-gpt-oss-20b | $0.07 | $0.3 | $0.007 | $0.07 | 131k | 8d agoout −0% |
| Neonopengpt-oss-20b | $0.07 | $0.3 | — | — | 131k | — |
| OCI Generative AIopenopenai.gpt-oss-20b | $0.07 | $0.3 | — | — | 128k | — |
| Ollama Cloudopengpt-oss:20b | $0.07 | $0.3 | $0.035 | — | 131k | — |
| Prime Inferenceopenopenai/gpt-oss-20b | $0.07 | $0.3 | — | — | 131k | — |
| Eden AIopengroq/openai/gpt-oss-20b | $0.075 | $0.3 | $0.0375 | — | 131k | — |
| Groqopenopenai/gpt-oss-20b | $0.075 | $0.3 | $0.0375 | — | 131k | — |
| AI/ML APIopenopenai/gpt-oss-20b | $0.0794 | $0.3174 | $0.0397 | — | 131k | 30d agoout −23.1% |
| DigitalOceanopenopenai-gpt-oss-20b | $0.05 | $0.45 | $0.01 | — | 128k | — |
| Hugging Faceopenopenai/gpt-oss-20b | $0.1 | $0.5 | — | — | 131k | — |
| LLM Gatewayopengroq/gpt-oss-20b | $0.1 | $0.5 | — | — | 131k | — |
| Regolo AIopengpt-oss-20b | $0.1121 | $0.471 | — | — | 128k | 31d ago |
| LowRouteropenauto/openai/gpt-oss-20b | $0.113 | $0.4745 | — | — | 131k | — |
| STACKITopenopenai/gpt-oss-20b | $0.18 | $0.29 | — | — | 131k | — |
| Opperopengpt-oss-20b | $0.1162 | $0.4881 | — | — | 128k | — |
| Cloudflare Workers AIopen@cf/openai/gpt-oss-20b | $0.2 | $0.3 | — | — | 128k | — |
| Eden AIopencloudflare/@cf/openai/gpt-oss-20b | $0.2 | $0.3 | — | — | 128k | — |
| Thinking Machinesopenopenai/gpt-oss-20b | $0.18 | $0.45 | $0.036 | — | 33k | — |
| InferAllfreeopenai/gpt-oss-20b | free | free | — | — | 131k | — |
| LMStudiofreeopenai/gpt-oss-20b | free | free | — | — | 131k | — |
| Nvidiafreeopenai/gpt-oss-20b | free | free | — | — | 131k | — |
| QVACfreegpt-oss-20b | free | free | — | — | 131k | — |
GPT OSS 20B price history
Output price per 1M tokens since tracking began on Sep 10, 2026, for the 6 cheapest of 13 providers whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| Kilo Gateway | $0.018 → $0.017 | $0.09 → $0.085 | −5.6% | |
| OpenRouter | $0.018 → $0.017 | $0.09 → $0.085 | −5.6% | |
| OpenRouter | $0.03 → $0.018 | $0.13 → $0.09 | −30.8% | |
| Kenari | $0.036 | $0.1543 → $0.1543 | +0% | |
| Eden AI | $0.07 | $0.3 → $0.3 | −0% | |
| NanoGPT | $0.02 → $0.018 | $0.03 → $0.09 | +200% | |
| Kilo Gateway | $0.004 → $0.018 | $0.017 → $0.09 | +429.4% | |
| NanoGPT | $0.004 → $0.02 | $0.017 → $0.03 | +76.5% | |
| Kilo Gateway | $0.009 → $0.004 | $0.037 → $0.017 | −54.1% | |
| NanoGPT | $0.007 → $0.004 | $0.027 → $0.017 | −37% | |
| Kilo Gateway | $0.005 → $0.009 | $0.019 → $0.037 | +94.7% | |
| NanoGPT | $0.005 → $0.007 | $0.021 → $0.027 | +28.6% | |
| NanoGPT | $0.008 → $0.005 | $0.035 → $0.021 | −40% | |
| Kilo Gateway | $0.006 → $0.005 | $0.027 → $0.019 | −29.6% | |
| Kilo Gateway | $0.011 → $0.006 | $0.047 → $0.027 | −42.6% | |
| NanoGPT | $0.016 → $0.01 | $0.067 → $0.04 | −40.3% | |
| Kilo Gateway | $0.015 → $0.011 | $0.063 → $0.047 | −25.4% | |
| NanoGPT | $0.01 → $0.008 | $0.04 → $0.035 | −12.5% | |
| OpenRouter | $0.018 → $0.03 | $0.09 → $0.13 | +44.4% | |
| NanoGPT | $0.02 → $0.016 | $0.1 → $0.067 | −33% |
GPT OSS 20B pricing FAQ
What is the cheapest GPT OSS 20B API?
As of Nov 22, 2026, SOKKAN Router has the lowest GPT OSS 20B output price at $0.075 per 1M tokens, and SOKKAN Router has the lowest input price at $0.015 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?
42 providers list GPT OSS 20B on Sovyron; 43 of them sell it at a metered per-token price.
Is GPT OSS 20B free?
4 providers list a free-tier offer: InferAll, 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.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—