DeepSeek
DeepSeek V3.1
deepseek/deepseek-chat-v3.1
Input
$0.25
per 1M tokens
Output
$0.95
per 1M tokens
Cached input
$0.13
per 1M tokens
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...
- Released
- Context window
- 164K tokens
- Max output
- 33K tokens
- Input
- text
- Output
- text
- Reasoning
- Yes
Price history
No price changes since we started tracking on .
Providers on OpenRouter
5 endpoints serve this model. Uptime is OpenRouter's share of successful requests; prices per 1M tokens.
| Provider | Input | Output | Context window | Uptime 30 min | Uptime 24 h |
|---|---|---|---|---|---|
| DeepInfrafp4 | $0.25 | $0.95 | 164K | 100% | 99.85% |
| SiliconFlowfp8 | $0.27 | $1.00 | 164K | 100% | 97.6% |
| SambaNovafp8 | $0.65 | $1.50 | 131K | — | 91.9% |
| CoreWeavefp8 | $0.55 | $1.65 | 161K | 100% | 100% |
| Mara | $0.60 | $1.70 | 131K | 100% | 93.3% |