DeepSeek V3.1
AvailableDeepSeek-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...
- Context
- 163.8K tokens
- Max output
- 32.8K tokens
- Input / 1M tokens
- $0.25per 1M tokens
- Output / 1M tokens
- $0.95per 1M tokens
- Listed since
- Aug 21, 2025
Prices and model data from OpenRouter
Where it's availableProviders · 1
| Provider | Input / 1M tokens | Output / 1M tokens | Status |
|---|---|---|---|
| OpenRouter | $0.25 | $0.95 | Available |
Published benchmark results
From independent leaderboards, each credited to its publisher.