Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team.
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 | $0.36 | $0.33 | per 1M tokens |
| Outputper 1M tokens | $1.20 | $1.10 | per 1M tokens |
| Cached inputper 1M tokens | $0.12 | $0.11 | per 1M tokens |
What an agent paid per million tokens, by day.
Unchanged since Sep 29, 2026: $0.36 in and $1.20 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 |
|---|---|---|
| GoogleUs south1, answering | 99.9% | 262K |
| DeepInfraTurbofp4, answering | 97.2% | 262K |
| VeniceFp8fp8, answering | 94.1% | 256K |
| NovitaFp8fp8, having trouble | 22.7% | 262K |
| AlibabaOpensource, answering | 100% | 262K |