Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
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 | $0.030 | $0.027 | per 1M tokens |
| Outputper 1M tokens | $5.22 | $4.80 | per 1M tokens |
| Cached inputper 1M tokens | $0.024 | $0.022 | per 1M tokens |
What an agent paid per million tokens, by day.
Unchanged since Sep 29, 2026: $0.030 in and $5.22 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 |
|---|---|---|
| Wafer, answering | 100% | 262K |
| Reka, answering | 99.7% | 262K |
| DarkbloomFp4fp4, answering | 99.3% | 262K |
| DekaLLM, answering | 99.5% | 262K |
| IonstreamFp8fp8, answering | 99.1% | 262K |
| Phala, answering | 98.6% | 1M |
| DeepInfraBf16bf16, having trouble | 98.5% | 262K |
| Mancer 2Fp8fp8, answering | 99.7% | 262K |
| AkashMLFp8fp8, answering | 99.8% | 262K |
| ParasailFp8fp8, answering | 100% | 262K |
| ChutesFp8fp8, answering | 99.3% | 262K |
| CoreWeaveFp8fp8, answering | 99.9% | 262K |
| Novita, answering | 99.9% | 1M |
| Alibaba, answering | 97.6% | 1M |
| Cloudflare, answering | 97.9% | 262K |
| VeniceFp8fp8, answering | 99.8% | 262K |