deepseek/deepseek-v4-pro
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. It is designed for advanced reasoning, coding,...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepSeekcache | $0.435 | $0.870 | 1.0M | 100% |
| Baidufp8 | $0.760 | $1.52 | 1.0M | 99.9% |
| StreamLake | $0.870 | $1.74 | 1.0M | 95.5% |
| GMICloudfp8 | $1.27 | $2.54 | 1.0M | 93.2% |
| DeepInfrafp4 | $1.30 | $2.60 | 1.0M | 94.4% |
| DigitalOcean | $1.48 | $2.96 | 1.0M | 95% |
| SiliconFlowfp8 | $1.60 | $3.13 | 1.0M | 99.8% |
| Novitafp8 | $1.60 | $3.20 | 1.0M | 98.9% |
| Alibaba | $1.61 | $3.22 | 1M | 99.7% |
| AtlasCloudfp8 | $1.68 | $3.38 | 1.0M | 99.4% |
| Venice | $1.73 | $3.80 | 1M | 96.8% |
| Parasailfp8 | $1.74 | $3.48 | 1.0M | — |
| Fireworks | $1.74 | $3.48 | 1.0M | 97.6% |
| Together | $1.74 | $3.48 | 512K | 95.4% |
| WandBfp8 | $1.74 | $3.48 | 1.0M | 98.2% |
| NextBitfp8 | $1.80 | $3.20 | 1.0M | — |
DeepSeek V4 Pro costs $0.435 per million input tokens and $0.870 per million output tokens via OpenRouter, making it 156th cheapest of 298 paid models.
DeepSeek V4 Pro scores 39.3 on the Artificial Analysis Intelligence Index, ranking 43rd of 180 benchmarked models, with a GPQA Diamond score of 72%.
DeepSeek V4 Pro generates around 62 tokens per second with 604ms time-to-first-token (p50), the 137th fastest tracked model.
DeepSeek V4 Pro supports a 1.0M-token context window and can output up to 384K tokens. It accepts text input.