DDeepSeek · Released Sep 22, 2025
DeepSeek V3.1 Terminus
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further…
- Released
- Sep 22 2025
- Context window
- 164K 147K out
- Input / 1M tokens
- $0.27 from $0.25
- Output / 1M tokens
- $1.00 from $0.70
Where to run it
9 providers compared
Cheapest: NanoGPT at $0.25 / $0.70 per 1M input / output tokens — 60% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| NanoGPT | $0.25 | $0.70 | $0.13 | 128K | 66K | — | Cheapest |
| SiliconFlowFP8 | $0.27 | $1.00 | — | 164K | 147K | 99.4%24h | +25% |
| Helicone | $0.27 | $1.00 | $0.22 | 128K | 16K | — | +25% |
| Kilo Gateway | $0.27 | $1.00 | — | 164K | 147K | — | +25% |
| Abacus | $0.27 | $1.00 | — | 128K | 8K | — | +25% |
| Alibaba (China) | $0.27 | $1.00 | — | 164K | 66K | — | +25% |
| StreamLakeno tool calling | $0.34 | $1.03 | — | 128K | 32K | 99.9%24h | +42% |
| Qiniu | $0.58 | $1.74 | — | 128K | 32K | — | +140% |
| SiliconFlow (China) | $0.60 | $1.79 | $0.06 | 164K | 164K | — | +147% |
Value
Price vs. performance
DeepSeek V3.1 Terminus Other DeepSeek Other labs Value frontier · SciCode vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
3 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| SciCodeSoftware engineering · Research-coding problems from the natural sciences | 38.0% | #84of 102 | Claude Opus 5.566.9% |
| CritPtReasoning & knowledge · Open-ended, research-level physics problems | 1.7% | #71of 111 | GPT-5.6 Sol32.3% |
| LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts | 28.6% | #84of 123 | Claude Sonnet 5.568.3% |
Specs
Details
- Model ID
deepseek/deepseek-v3.1-terminus- Developer
- DeepSeek
- Release date
- Sep 22, 2025 ·
- Context window
- 163,840 tokens
- Max output
- 147,456 tokens
- API price
- $0.27 / $1.00 per 1M input / output tokens
- Providers
- 9
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; 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.