DeepSeek: V3.1 Terminus
DeepSeek chat model for instruction following, coding, and analysis
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↓ lowerOutput $1 → $0.7
- ↓ lowerInput $0.27 → $0.25
- ↑ higherOutput $0.79 → $1
- ↑ higherInput $0.21 → $0.27
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestdeepseek-ai/DeepSeek-V3.1-Terminus | NanoGPT | $0.25 | $0.7 | $0.125 | 128K |
| models.devcheapestdeepseek-ai/DeepSeek-V3.1-Terminus:thinking | NanoGPT | $0.25 | $0.7 | $0.125 | 128K |
| models.devdeepseek-ai/DeepSeek-V3.1-Terminus | Abacus | $0.27 | $1 | $0 | 128K |
| models.devdeepseek-ai/DeepSeek-V3.1-Terminus | SiliconFlow | $0.27 | $1 | $0 | 164K |
| models.devsiliconflow/deepseek-v3.1-terminus | Alibaba / Qwen | $0.27 | $1 | $0 | 164K |
| models.devdeepseek-v3.1-terminus | Helicone | $0.27 | $1 | $0.216 | 128K |
| models.devdeepseek/deepseek-v3.1-terminus | Kilo Gateway | $0.27 | $1 | $0 | 164K |
| OpenRouterdeepseek/deepseek-v3.1-terminus | OpenRouter | $0.27 | $1 | $0 | 164K |
| LiteLLMdeepseek-ai/DeepSeek-V3.1-Terminus | N/A | $0.27 | $1 | $0.216 | N/A |
| LiteLLMDeepSeek-V3.1-Terminus | N/A | $0.27 | $1 | $0.216 | N/A |
| LiteLLMdeepseek/deepseek-v3.1-terminus | N/A | $0.27 | $1 | $0.135 | N/A |
| LiteLLMdeepinfra/deepseek-ai/DeepSeek-V3.1-Terminus | N/A | $0.27 | $1 | $0.216 | N/A |
| LiteLLMnovita/deepseek/deepseek-v3.1-terminus | N/A | $0.27 | $1 | $0.135 | N/A |
| LiteLLMaccounts/fireworks/models/deepseek-v3p1-terminus | N/A | $0.56 | $1.68 | $0.056 | N/A |
| LiteLLMdeepseek-v3p1-terminus | N/A | $0.56 | $1.68 | $0.056 | N/A |
| LiteLLMfireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus | N/A | $0.56 | $1.68 | $0.056 | N/A |
| models.devdeepseek/deepseek-v3.1-terminus | Qiniu | $0.5797 | $1.74 | $0 | 128K |
| models.devdeepseek/deepseek-v3.1-terminus-thinking | Qiniu | $0.5797 | $1.74 | $0 | 128K |
| models.devPro/deepseek-ai/DeepSeek-V3.1-Terminus | SiliconFlow (China) | $0.5978 | $1.79 | $0.0598 | 164K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence14.8i
- AA coding43.5i
- AA agentic6.8i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.