DataLearner logo
DE

DeepSeek-V3.1 Terminus

Chat modelDeepSeek VDeepSeek V3.1

DeepSeek-V3.1 Terminus

Release date: 2025-09-22Updated: 2026-06-15Views: 1,716
Parameters
671B
Context length
128K
Multilingual
Supported
Reasoning ability
4/5

DeepSeek-V3.1 Terminus is an AI model published by DeepSeek-AI, released on 2025-09-22, for Chat model, with 671B parameters, and 128K context length, requiring about 1340GB storage, with a 96.80 score on SimpleQA.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

DeepSeek-V3.1 Terminus

Model basics

Reasoning traces
Supported
Thinking modes
Standard Mode (Default)Thinking Mode
Context length
128K tokens
Max output length
8K tokens
Model type
Chat model
Modality (in / out)
Text → Text
Release date
2025-09-22
Model file size
1340GB
MoE architecture
Yes
Total params / Active params
671B / 37B
Knowledge cutoff
No data
DeepSeek-V3.1 Terminus

Open source & experience

Code license
Weights license
MIT License- Commercial use permitted
DeepSeek-V3.1 Terminus

Official resources

Paper
DataLearnerAI blog
N/A
DeepSeek-V3.1 Terminus

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$0.210/ 1M$0.790/ 1M
Cache PricingPrompt Cache
TypeTTLWriteRead
Text-$0.210/ 1M$0.168/ 1M
Text-$0.210/ 1M
Cache = write
Text-$0.168/ 1M
Cache = hit

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

DeepSeek-V3.1 Terminus

Benchmark Results

DeepSeek-V3.1 Terminus currently shows benchmark results led by SimpleQA (2 / 47, score 96.80), MMLU Pro (27 / 133, score 85), LiveCodeBench (33 / 127, score 80). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Knowledge

4 evaluations
Benchmark / mode
Score
Rank/total
MMLU Pro
Standard Mode
85
27 / 133
MMLU Pro
Thinking Mode
85
27 / 133
HLE
Standard Mode
21.70
123 / 185
HLE
Thinking Mode
15.20
147 / 185

General Evaluation

2 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
80.70
140 / 270
GPQA Diamond
Thinking Mode
79
150 / 270

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
Standard Mode
96.80
2 / 47

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Standard Mode
74.90
43 / 127
LiveCodeBench
Thinking Mode
80
33 / 127
SWE-bench Verified
Standard Mode
68.40
69 / 114

Math and Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Standard Mode
54
85 / 106
AIME2025
Thinking Mode
90
37 / 106

AI Agent - Tool Usage

2 evaluations
Benchmark / mode
Score
Rank/total
Terminal-Bench
Standard ModeTools
30
22 / 35
Terminal-Bench
Thinking ModeTools
28
24 / 35

Agent Level Benchmark

2 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench
Standard ModeTools
37
39 / 43
τ²-Bench
Thinking ModeTools
37
39 / 43
DeepSeek-V3.1 Terminus

Publisher

DeepSeek-V3.1 Terminus

Model Overview

DeepSeek-V3.1 Terminus is an AI model published by DeepSeek-AI, released on 2025-09-22, for Chat model, with 671B parameters, and 128K context length, requiring about 1340GB storage, with a 96.80 score on SimpleQA.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code