DeepSeek-V3.1-Terminus-Thinking
DeepSeek-V3.1-Terminus-Thinking is a reasoning model from DeepSeek released on Sep 22, 2025. It reads text and writes text, with a 128K token context window and up to 32K tokens per reply.
- Modalities
- In / out price
- n/a
- Context
- 128K
- Max output
- 32K
- Released
- Sep 22, 2025
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Supported request parameters
What you can set when you call DeepSeek-V3.1-Terminus-Thinking through an OpenAI compatible API.
- Reasoning
reasoning - Temperature
temperature
More from DeepSeek
- 1.05M context
Reads text and images. Tool calling, reasoning.
by deepseekOct 13, 2026$0.15/M input tokens$0.60/M output tokens
- Index 39.5
Reads text and images. Tool calling, structured output, reasoning. Served by 55 providers.
by deepseekSep 10, 20261M context$0.15/M input tokens$0.60/M output tokens55 providers
- 1.05M context
Reads text and images. Tool calling, structured output, reasoning. Served by 14 providers.
by deepseekAug 21, 2026$0.44/M input tokens$1.32/M output tokens14 providers
- 1.05M context
Reads text. Tool calling, structured output, reasoning. Served by 32 providers.
by deepseekAug 12, 2026$1.32/M input tokens$3.96/M output tokens32 providers
- 1.05M context
Reads text. Tool calling, structured output, reasoning. Served by 44 providers.
by deepseekJul 31, 2026$0.14/M input tokens$0.28/M output tokens44 providers
- 1.05M context
Reads text. Tool calling, structured output, reasoning. Served by 2 providers.
by deepseekJul 31, 2026$0.14/M input tokens$0.28/M output tokens2 providers
DeepSeek-V3.1-Terminus-Thinking questions
What is the context window of DeepSeek-V3.1-Terminus-Thinking?
128,000 tokens of input, and it can write up to 32,000 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Does DeepSeek-V3.1-Terminus-Thinking support tool calling?
Not through the standard tools parameter. For an agent that calls your APIs, pick a model from the alternatives below that does.
Is DeepSeek-V3.1-Terminus-Thinking open source?
No. DeepSeek serves it through an API only, so you cannot download the weights or host it yourself.
When was DeepSeek-V3.1-Terminus-Thinking released?
Sep 22, 2025.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on DeepSeek-V3.1-Terminus-Thinking?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting