gpt-oss-20b API pricing
As of October 22, 2026, OpenAI gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens, the median of 11 providers on OpenRouter, with cached input at $0.009 per million.
gpt-oss-20b benchmarks and specs · Every OpenAI model's price
- Input, per million tokens$0.03
- Output, per million tokens$0.15
- Cached input, per million$0.009
- Context window131K tokens
- Max output33K tokens
- Output speed290 tok/s
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0001 | $0.105 | Yes |
| Repository review | 50K input + 3K output tokens | $0.0019 | $1.95 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.0075 | $7.50 | No, it would need splitting |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | Not computable | Not computable |
Price history
The price of gpt-oss-20b here is the median across 11 providers on OpenRouter, so we do not track price changes for it.
Cheaper models as good as gpt-oss-20b
Models within two points of gpt-oss-20b or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.
No model at least as good on this index costs less per output token.
gpt-oss-20b pricing questions
- How much does gpt-oss-20b cost per million tokens?
- $0.03 per million input tokens and $0.15 per million output tokens, as listed on OpenRouter on October 22, 2026.
- Does gpt-oss-20b support prompt caching?
- Yes. OpenRouter lists cached input at $0.009 per million tokens, against $0.03 for uncached input.
- Has the price of gpt-oss-20b changed?
- The price of gpt-oss-20b here is the median across 11 providers on OpenRouter, so we do not track price changes for it.