deepseek/deepseek-chat-v3.1
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrafp4 | $0.210 | $0.790 | 164K | 97.2% |
| Novitafp8 | $0.270 | $1.00 | 131K | 100% |
| SiliconFlowfp8 | $0.270 | $1.00 | 164K | 97.4% |
| AtlasCloudfp8 | $0.300 | $0.950 | 131K | 100% |
| WandBfp8 | $0.550 | $1.65 | 161K | 100% |
| $0.600 | $1.70 | 164K | 99.9% | |
| SambaNovafp8 | $0.650 | $1.50 | 131K | 98.9% |
DeepSeek V3.1 costs $0.210 per million input tokens and $0.790 per million output tokens via OpenRouter, making it 103rd cheapest of 298 paid models.
DeepSeek V3.1 scores 28.1 on the Artificial Analysis Intelligence Index, ranking 84th of 180 benchmarked models, with a GPQA Diamond score of 74%.
DeepSeek V3.1 generates around 85 tokens per second with 368ms time-to-first-token (p50), the 87th fastest tracked model.
DeepSeek V3.1 supports a 164K-token context window and can output up to 33K tokens. It accepts text input.