DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.
Prices for the AI credit you buy. $BINF holders pay up to 8% less.
| Charge | Price | Holders | Per |
|---|---|---|---|
| Inputper 1M tokens | $0.72 | $0.66 | per 1M tokens |
| Outputper 1M tokens | $1.20 | $1.10 | per 1M tokens |
| Cached inputper 1M tokens | $0.20 | $0.18 | per 1M tokens |
The price per million tokens, by day.
Today · $0.72 in · $1.20 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 |
|---|---|---|
| BaiduFp8fp8, answering | 99.9% | 1M |
| StreamLakeFp8fp8, answering | 100% | 1M |
| RelaceFp4fp4, answering | 100% | 1M |
| GMICloudFp8fp8, answering | 99.9% | 1M |
| SiliconFlowFp8fp8, answering | 100% | 1M |
| DigitalOcean, answering | 100% | 1M |
| DeepInfraFp8fp8, answering | 100% | 1M |
| AlibabaFp8fp8, answering | 97.5% | 1M |
| AlibabaFp8fp8, answering | 100% | 1M |
| NovitaFp8fp8, answering | 100% | 1M |
| Venice, answering | 89.5% | 1M |
| AtlasCloudFp4fp4, answering | 100% | 1M |
| AzureUS, answering | 100% | 1M |