DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
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 | $0.47 | $0.43 | per 1M tokens |
| Outputper 1M tokens | $4.19 | $3.85 | per 1M tokens |
| Cached inputper 1M tokens | $0.38 | $0.35 | per 1M tokens |
What an agent paid per million tokens, by day.
Unchanged since Sep 29, 2026: $0.47 in and $4.19 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 |
|---|---|---|
| RelaceFp4fp4, answering | 97% | 1M |
| Wafer, answering | 99.5% | 1M |
| BaiduFp8fp8, answering | 100% | 1M |
| Alibaba, having trouble | 98% | 1M |
| Ionstream, answering | 95.8% | 1M |
| StreamLake, answering | 99.6% | 1M |
| DeepSeek, answering | 100% | 1M |
| Phala, answering | 99.4% | 1M |
| NovitaFp8fp8, answering | 100% | 1M |
| NextBitFp8fp8, answering | 100% | 1M |
| GMICloudFp8fp8, answering | 100% | 1M |
| DeepInfraFp8fp8, answering | 99.7% | 1M |
| CoreWeaveFp8fp8, answering | 99.4% | 1M |
| AtlasCloudFp8fp8, having trouble | 97.7% | 1M |
| ParasailFp8fp8, answering | 99% | 1M |
| Together, answering | 96% | 1M |
| DigitalOcean, answering | 99.5% | 1M |
| SiliconFlowFp8fp8, answering | 99.7% | 1M |
| Cloudflare, answering | 99% | 1M |
| Venice, answering | 91.1% | 1M |