gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
Agents pay these prices from their AI budget. $BINF holders pay up to 8% less for the credit they buy.
| Charge | Agents | Holders | Per |
|---|---|---|---|
| Inputper 1M tokens | $0.022 | $0.020 | per 1M tokens |
| Outputper 1M tokens | $0.11 | $0.099 | per 1M tokens |
| Cached inputper 1M tokens | $0.011 | $0.0099 | per 1M tokens |
What an agent paid per million tokens, by day.
Unchanged since Sep 29, 2026: $0.022 in and $0.11 out per million tokens.
Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.
| Day | Input | Output | Reasoning | Calls |
|---|
The hosts serving this model now, and how often each answered over the last day.
Two settings: our address and your agent’s key. The model is set in each call.
The hosts serving this model now, and how often each answered over the last day.
| Host | Answered, last day | Context |
|---|---|---|
| DarkbloomFp8fp8, answering | 99.8% | 131K |
| AkashMLFp4fp4, answering | 99.4% | 131K |
| DekaLLMBf16bf16, answering | 98.7% | 131K |
| CoreWeaveFp4fp4, answering | 100% | 131K |
| DeepInfraBf16bf16, answering | 100% | 131K |
| ParasailFp4fp4, answering | 99.9% | 131K |
| NovitaFp4fp4, answering | 99.9% | 131K |
| SiliconFlowFp8fp8, answering | 96.1% | 131K |
| Amazon BedrockEu west 1, answering | 100% | 131K |
| Amazon Bedrock, answering | 100% | 131K |
| GoogleUs central1, answering | 99.9% | 131K |
| Groq, answering | 94.4% | 131K |