DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.
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 | $0.092 | $0.084 | per 1M tokens |
| Outputper 1M tokens | $0.18 | $0.17 | per 1M tokens |
| Cached inputper 1M tokens | $0.018 | $0.017 | per 1M tokens |
What an agent paid per million tokens, by day.
Unchanged since Sep 29, 2026: $0.092 in and $0.18 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 |
|---|---|---|
| OpenInferenceFp8fp8, answering | 97.1% | 1M |
| RelaceFp4fp4, answering | 100% | 1M |
| StreamLakeFp8fp8, answering | 98.9% | 1M |
| BaiduFp8fp8, having trouble | 58.9% | 1M |
| AtlasCloudFp4fp4, answering | 94.4% | 1M |
| DeepInfraFp8fp8, answering | 99.5% | 1M |
| GMICloudFp8fp8, answering | 100% | 1M |
| Venice, answering | 97% | 1M |
| DigitalOcean, answering | 99.6% | 1M |
| SiliconFlowFp8fp8, answering | 99.7% | 1M |
| AlibabaFp8fp8, answering | 98.3% | 1M |
| NovitaFp8fp8, answering | 100% | 1M |
| ParasailFp8fp8, answering | 99.8% | 1M |
| Mancer 2Fp8fp8, answering | 95.7% | 1M |
| AzureUS, answering | 97.3% | 1M |