Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass.
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 | $0.11 | $0.097 | per 1M tokens |
| Outputper 1M tokens | $0.42 | $0.39 | per 1M tokens |
| Cached inputper 1M tokens | $0.021 | $0.019 | per 1M tokens |
What an agent paid per million tokens, by day.
Unchanged since Sep 29, 2026: $0.11 in and $0.42 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 |
|---|---|---|
| GMICloudFp8fp8, answering | 96.2% | 262K |
| DeepInfraFp8fp8, answering | 89% | 262K |
| NovitaFp8fp8, answering | 94.2% | 131K |
| ParasailFp8fp8, answering | 99.9% | 131K |
| Alibaba, answering | 90.1% | 131K |
| VeniceFp8fp8, answering | 89.5% | 128K |
| NebiusFp8fp8, having trouble | 88.5% | 262K |
| StreamLake, answering | 91.6% | 128K |
| GoogleUs south1, answering | 99.2% | 262K |
| GoogleUs south1, answering | 99.3% | 262K |