> DeepSeek-V3.1 is an open-weights AI model from DeepSeek, released 21 Aug 2025. Index score 132 (GPT-4 = 100), rank 111 of 229 ranked models. API price $0.25 in / $0.95 out per million tokens, 164K context.

[Models](https://themodelindex.org/models/) /[DeepSeek](https://themodelindex.org/labs/deepseek/)

# DeepSeek-V3.1

DeepSeek

Released 21 Aug 2025

Open

[Compare](https://themodelindex.org/compare/deepseek-v3-1-vs-gpt-5/) [Announcement](https://api-docs.deepseek.com/news/news250821/)

132120–144

Index score

#111 · provisional, limited data

0/ 8

Core tests taken

0 of 6 areas · plus 5 anchor tests

−22

Versus the frontier at release

best then: GPT-5

Replaced by [DeepSeek-V3.2-Exp](https://themodelindex.org/models/deepseek-v3-2-exp/)

$0.25/ $0.95

Price per million tokens

input / output, list price

164K

Context window

tokens it reads at once

## Where it sits · on the frontier

_Chart: Model Index score of every scored model since late 2022, with the best closed and best open model over time_

o1 reached this score 9 months earlier.

## Test results · by area · tick = best by any model

Show 4 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

no result

Humanity's Last Exam

no result

Maths

no evidence yet

FrontierMath T1-3

no result

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

evidence

APEX-Agents

no result

Novel problems

no evidence yet

ARC-AGI-2

no result

Long tasks

no evidence yet

METR time horizon

no result

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

## What others say · rank on each leaderboard

The Model Index

independent tests, our method

#111

of 219 · 132

LMArena · Creative writing

creative writing

#93

of 386 · 1402

LMArena · Text

overall chat quality, judged by people

#116

of 388 · 1417

LMArena · Maths

maths questions in chat

#120

of 373 · 1414

LMArena · Coding

coding questions in chat

#130

of 383 · 1456

Epoch Capabilities Index

overall capability from many benchmarks

#105

of 239 · 139.9

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.

## Best at · top three among current models

Replaced by DeepSeek-V3.2-Exp; it no longer leads any category among current models.

Where this model places in the top three of today's models, on category leaderboards and on our core tests.

## Where to use it · prices checked 1 Oct 2026

#### From the lab

DeepSeek Chat

app · subscription

↗

DeepSeek API

API

↗

#### API providers · 7 · per million tokens, in / out

D

DeepInfra

$0.25 / $0.95 · fp4

cheapest

S

SiliconFlow

$0.27 / $1.0 · fp8

↗

A

AtlasCloud

$0.30 / $1.0 · fp8

↗

C

CoreWeave

$0.55 / $1.65 · fp8

↗

S

SambaNova

$0.65 / $1.5 · fp8

↗

M

Mara

$0.60 / $1.7

↗

G

Google

$0.60 / $1.7

↗

#### Run it yourself

🤗

Official weights

deepseek-ai/DeepSeek-V3.1

↗

Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps.

## Facts and sources

Released

21 Aug 2025

Announcement

[api-docs.deepseek.com ↗](https://api-docs.deepseek.com/news/news250821/)

Release entry

DeepSeek-V3.1 (hybrid reasoning)

Scored as

DeepSeek-V3.1

Artificial Analysis index

–

Output speed

–

Hugging Face

[deepseek-ai/DeepSeek-V3.1 ↗](https://huggingface.co/deepseek-ai/DeepSeek-V3.1)

## DeepSeek releases · around this one

DeepSeek-R1

Open

20 JAN 2025

index 129

DeepSeek-R1-0528

Open

28 MAY 2025

index 134

DeepSeek-V3.1

Open

21 AUG 2025

index 132

DeepSeek-V3.2-Exp

Open

29 SEP 2025

index 143

DeepSeekMath-V2

Open

27 NOV 2025

---
Source: https://themodelindex.org/models/deepseek-v3-1/ · The Model Index · data as of 2026-10-01