DeepSeek V3.1 Terminus
DeepSeek chat model for instruction following, coding, and analysis
Cheapest input
$0.25
$/MTok · models.dev
Cheapest output
$0.7
$/MTok
Context
164K
tokens
Offers
5
2 sources
Offers
Same model, different listings. First-party, 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 | 128K |
| models.devdeepseek-ai/DeepSeek-V3.1-Terminus | Abacus | $0.27 | $1 | $0 | 128K |
| models.devdeepseek-ai/DeepSeek-V3.1-Terminus | SiliconFlow (China) | $0.27 | $1 | $0 | 164K |
| models.devdeepseek-ai/DeepSeek-V3.1-Terminus | SiliconFlow | $0.27 | $1 | $0 | 164K |
| LiteLLMdeepseek-ai/DeepSeek-V3.1-Terminus | — | $0.27 | $1 | $0.216 | — |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Released: 2025-06-01Family: deepseek
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence30.4
- AA coding43.5
- AA agentic18.1
Sources: Arena AI, Artificial Analysis. See /benchmarks.