deepseek/deepseek-chat-v3-0324
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrafp4 | $0.200 | $0.770 | 164K | 99.8% |
| AtlasCloudfp8 | $0.216 | $0.880 | 131K | 99.9% |
| ModelRunfp4 | $0.220 | $0.800 | 164K | 99.7% |
| SiliconFlowfp8 | $0.250 | $1.00 | 164K | 99.2% |
| Novitafp8 | $0.270 | $1.12 | 164K | 100% |
| GMICloudfp8 | $0.290 | $1.14 | 164K | — |
DeepSeek V3 0324 costs $0.200 per million input tokens and $0.770 per million output tokens via OpenRouter, making it 99th cheapest of 298 paid models.
DeepSeek V3 0324 scores 22.3 on the Artificial Analysis Intelligence Index, ranking 112th of 180 benchmarked models, with a GPQA Diamond score of 66%.
DeepSeek V3 0324 generates around 35 tokens per second with 900ms time-to-first-token (p50), the 224th fastest tracked model.
DeepSeek V3 0324 supports a 164K-token context window and can output up to 16K tokens. It accepts text input.