DDeepSeek · Released Aug 21, 2025
DeepSeek V3.1
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
- Aug 21 2025
- Context window
- 164K 33K out
- Input / 1M tokens
- $0.25
- Output / 1M tokens
- $0.95
Where to run it
5 providers compared
Cheapest: DeepInfra at $0.25 / $0.95 per 1M input / output tokens — 51% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| DeepInfraFP4 | $0.25 | $0.95 | $0.13 | 164K | 33K | 100%24h | Cheapest |
| SiliconFlowFP8 | $0.27 | $1.00 | — | 164K | 147K | 97.4%24h | +6% |
| CoreWeaveFP8 | $0.55 | $1.65 | $0.55 | 161K | 145K | 100%24h | +94% |
| SambaNovaFP8 | $0.65 | $1.50 | — | 131K | 7K | 93.1%24h | +103% |
| Marano tool calling | $0.60 | $1.70 | — | 131K | 118K | 94.9%24h | +106% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated DeepSeek V3.1. Scores appear here automatically once it does.
Specs
Details
- Model ID
deepseek/deepseek-chat-v3.1- Developer
- DeepSeek
- Release date
- Aug 21, 2025 ·
- Context window
- 163,840 tokens
- Max output
- 32,768 tokens
- API price
- $0.25 / $0.95 per 1M input / output tokens
- Providers
- 5
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.