Skip to main content

DeepSeek V3.1 (Non-reasoning)

DeepSeekDeepSeekOpen WeightMIT · Commercial OK

Description

DeepSeek-V3.1 is a hybrid model supporting both thinking and non-thinking modes through different chat templates. Built on DeepSeek-V3.1-Base with a two-phase long context extension (32K phase: 630B tokens, 128K phase: 209B tokens), it features 671B total parameters with 37B activated. Key improvements include smarter tool calling through post-training optimization, higher thinking efficiency achieving comparable quality to DeepSeek-R1-0528 while responding more quickly, and UE8M0 FP8 scale data format for model weights and activations. The model excels in both reasoning tasks (thinking mode) and practical applications (non-thinking mode), with particularly strong performance in code agent tasks, math competitions, and search-based problem solving.

Release Date
2025-08-21
Parameters
671.0B
Context Length
164K
Modalities
text

Capability Radar

60
general
60
coding
60
reasoning
60
scienceest.
30
agents
0
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Factuality

SimpleQA93.4%SR

General

Aider-Polyglot68.4%SR

Language

MMLU-Redux91.8%SR
MMLU-Pro83.7%SR

Math

CodeForces0.70 / 3000SR
AIME 202466.3%SR
AIME 202549.8%SR
HMMT 202533.5%SR

Reasoning

GPQANYU + Cohere + Anthropic (2023)74.9%SR
SWE-Bench Verified66.0%SR
LiveCodeBench56.4%SR
SWE-bench Multilingual54.5%SR
BrowseComp-zh49.2%SR
Terminal-Bench31.3%SR
BrowseCompOpenAI (2025)30.0%SR
Humanity's Last Exam15.9%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Language
90
Factuality
90
Legal
80
Finance
80
Healthcare
80
Physics
70
Frontend Development
70
Biology
70
Chemistry
70
Math
60
Reasoning
60
General
60
Code
60
Search
40
Agents
30
Vision
20

Pricing

Input Price$0.53 / 1M tokens
Output Price$1.59 / 1M tokens
Blended Price (3:1)$0.425 / 1M tokens
Cache Read Price$0.13 / 1M tokens

Speed

Tokens/sec91.4
Time to First Token1.29s
Time to Answer1.29s

Provider Price Ranking

Provider Price Ranking

5 providers

Cheapest: DeepInfraMost Expensive: Alibaba (China)
ProviderInputOutput
1DeepInfraCheapest
$0.25
$0.95
2OpenRouter
$0.25
$0.95
3Kilo Gateway
$0.25
$0.95
4DeepSeekPRIMARY
$0.53
$1.59
5Alibaba (China)
$0.574
$1.721

Compare pricing across different API providers for this model.

External Sources