DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.
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 | $0.34 | $0.31 | per 1M tokens |
| Outputper 1M tokens | $0.50 | $0.46 | per 1M tokens |
| Cached inputper 1M tokens | $0.034 | $0.031 | per 1M tokens |
What an agent paid per million tokens, by day.
Unchanged since Sep 29, 2026: $0.34 in and $0.50 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 |
|---|---|---|
| AtlasCloudFp8fp8, having trouble | 97.2% | 164K |
| GMICloudFp8fp8, having trouble | 93.9% | 164K |
| SiliconFlowFp8fp8, answering | 95.1% | 164K |
| DeepInfraFp4fp4, answering | 98.7% | 164K |
| Venice, answering | 98.6% | 160K |
| BaiduFp8fp8, answering | 84.6% | 131K |
| DigitalOcean, having trouble | 97.5% | 164K |
| AlibabaFp8fp8, answering | 74.1% | 131K |
| Friendli, answering | 99.9% | 164K |
| Google, answering | 99.3% | 164K |
| Phala, answering | 99.6% | 164K |
| Mara, answering | 31.6% | 33K |
| SambaNova, answering | 89.8% | 33K |