ModelBeat
Models/DeepSeek-V3.1-Terminus
All models
D

DeepSeek: DeepSeek-V3.1-Terminus

deepseek/deepseek-v3.1-terminus

DeepSeek-V3.1-Terminus is DeepSeek’s open-weights AI model, released Sep 22, 2025. It costs $0.27/M input and $1/M output tokens, and handles a 164K-token context window.

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 optimizing the model's…

Context
164K
Input
$0.27 / 1M
Output
$1 / 1M
Released
Sep 22, 2025
Modalities
texttext

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where DeepSeek-V3.1-Terminus lands among all models tracked on Model Beat.

37.0
Intelligence Index
Artificial Analysis
37th percentile of tracked models
45.0
Coding Index
Artificial Analysis
45th percentile of tracked models
13.0
Agentic Index
Artificial Analysis
13th percentile of tracked models

Reasoning

3 evals
GPQA Diamond79.2%

Graduate-level scientific reasoning

Humanity's Last Exam15.2%

Frontier of human expert knowledge

MMLU-Pro85.1%

Broad expert knowledge

Coding

2 evals
LiveCodeBench79.8%

Contamination-free coding

SciCode40.6%

Scientific research coding

Math

1 evals
AIME 2024/202589.7%

Olympiad-qualifier math

Agentic & Tools

1 evals
τ²-bench37.1%

Tool-agent-user reliability

Compare DeepSeek-V3.1-Terminus with

Frequently asked questions

What is 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 optimizing the model's…

Who created DeepSeek-V3.1-Terminus?

DeepSeek-V3.1-Terminus is an AI model developed by DeepSeek, part of the DeepSeek family, released Sep 22, 2025.

How much does DeepSeek-V3.1-Terminus cost?

DeepSeek-V3.1-Terminus is served from $0.27 per million input tokens and $1 per million output tokens (cheapest credible provider on OpenRouter: SiliconFlow).

What is DeepSeek-V3.1-Terminus's context window?

DeepSeek-V3.1-Terminus supports a context window of up to 164K tokens.

How does DeepSeek-V3.1-Terminus perform on benchmarks?

On standardized evaluations tracked by Epoch AI, DeepSeek-V3.1-Terminus scores 85.1% on MMLU-Pro, 79.8% on LiveCodeBench, 89.7% on AIME 2024/2025.

Is DeepSeek-V3.1-Terminus open source?

DeepSeek-V3.1-Terminus is released with open weights (Open weights (unrestricted)), so the model can be downloaded and self-hosted.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Aug 5, 2026.