DeepSeek V3.1 Terminus: pricing, context and benchmarks

What you need to know about DeepSeek V3.1 Terminus

DeepSeek V3.1 Terminus was released by DeepSeek (China) on September 22, 2025. It accepts text as input and produces text. Its context window reaches 163,840 tokens, larger than 32 % of the models in the registry, and it can write up to 147,456 tokens in one go.

It has been available for about 13 months, long enough for its prices and scores to have settled.

DeepSeek V3.1 Terminus pricing

On OpenRouter, DeepSeek V3.1 Terminus costs $0.27 per million input tokens and $1 per million output tokens. Counting three tokens read for every token written, its average price is $0.453 per million, more expensive than 39 % of paid models (1.7 times cheaper than the median of $0.76).

A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.001. At 1,000 tasks a day, budget $31 a month. The price calculator redoes this with your own volumes.

Performance and benchmarks

Epoch AI does not yet publish a capabilities index for DeepSeek V3.1 Terminus. We therefore show no made-up performance rating: only price, context and features count towards its score.

Features, privacy and local use

• It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
• It can answer in an enforced JSON format (structured outputs).
• It is a reasoning model: it "thinks" before answering, which helps on hard tasks but uses more output tokens.
• Its knowledge stops at March 2025.

Its weights are open and downloadable from Hugging Face (mit licence): you can run it on your own machines without sending your data to a third party. With 684,531,386,000 billion parameters, it needs about 382,511,719,689 GB of memory at 4-bit quantisation. Check with the VRAM calculator. It was downloaded 12,966 times on Hugging Face last month.

Other DeepSeek models