deepseek/deepseek-chat
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| StreamLake | $0.200 | $0.800 | 128K | 99.8% |
| DeepInfrafp4 | $0.320 | $0.890 | 164K | 94.8% |
| Novitafp8 | $0.400 | $1.30 | 64K | 100% |
DeepSeek V3 costs $0.200 per million input tokens and $0.800 per million output tokens via OpenRouter, making it 102nd cheapest of 298 paid models.
DeepSeek V3 generates around 26 tokens per second with 595ms time-to-first-token (p50), the 260th fastest tracked model.
DeepSeek V3 supports a 131K-token context window and can output up to 16K tokens. It accepts text input.