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.
Prices for the AI credit you buy. $BINF holders pay up to 8% less.
| Charge | Price | Holders | Per |
|---|---|---|---|
| Inputper 1M tokens | $0.11 | $0.10 | per 1M tokens |
| Outputper 1M tokens | $0.64 | $0.59 | per 1M tokens |
| Cached inputper 1M tokens | $0.040 | $0.037 | per 1M tokens |
The price per million tokens, by day.
Today · $0.11 in · $0.64 out per 1M 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 |
|---|---|---|
| DeepInfraFp8fp8, answering | 98.5% | 262K |
| ParasailFp8fp8, answering | 99.4% | 131K |
| VeniceFp8fp8, answering | 99.6% | 128K |
| NebiusFp8fp8, answering | 95% | 262K |