gpt-oss-20b
gpt-oss-20b is a general-purpose chat-tuned model. Available via OpenAI. 131,072-token context. Budget pricing.
gpt-oss-20b is a efficient AI model from OpenAI. It costs $0.0300 per million input tokens and $0.1300 per million output tokens (blended $0.0600/M), with a 131,072-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
-4.8%over 91 days · hover to read
From OpenRouter's listing, read on 17 Nov 2026.
- Solid general chat performance
- Reasonable instruction following
- General chat
- Drafting and rewriting
- Personal productivity
Benchmarks
More from OpenAI
See all 28 →Price history
3 recorded changes| Date | Rate | Was | Now | Change |
|---|---|---|---|---|
| 10 Nov 2026 | Output | $0.1400 | $0.1300 | -7.1% |
| 26 Jul 2026 | Input | $0.0290 | $0.0300 | +3.4% |
| 31 May 2026 | Input | $0.0300 | $0.0290 | -3.3% |
Rates per million tokens, as published by the provider or its router listing. Tracking runs since 3 May; anything earlier is not on record. See every tracked price change.
Frequently asked questions
How much does gpt-oss-20b cost?
gpt-oss-20b costs $0.0300 per million input tokens and $0.1300 per million output tokens, for a blended reference rate of $0.0600 per million tokens.
What is gpt-oss-20b's context window?
gpt-oss-20b supports up to 131,072 tokens of context in a single request.
What is gpt-oss-20b best for?
gpt-oss-20b is well suited to Solid general chat performance, Reasonable instruction following and General chat.
Who makes gpt-oss-20b?
gpt-oss-20b is developed and served by OpenAI.
