> DeepSeek-V4-Flash (Apr 2026) is an open-weights AI model from DeepSeek, released 24 Apr 2026. Index score 145 (GPT-4 = 100), rank 69 of 229 ranked models. API price $0.042 in / $0.084 out per million tokens, 1.05M context.

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

# DeepSeek-V4-Flash (Apr 2026)

DeepSeek

Released 24 Apr 2026

Open

[Compare](https://themodelindex.org/compare/deepseek-v4-flash-vs-gpt-5-5/)

145132–158

Index score

#69 · provisional, limited data

0/ 8

Core tests taken

0 of 6 areas · plus 4 anchor tests

−32

Versus the frontier at release

best then: GPT-5.5

Replaced by [DeepSeek-V4-Flash](https://themodelindex.org/models/deepseek-v4-flash-2026-07/)

$0.042/ $0.084

Price per million tokens

input / output, list price

1.05M

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_

o3 reached this score 12 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

#69

of 219 · 145

Epoch Capabilities Index

overall capability from many benchmarks

#31

of 239 · 154.5

LMArena · Creative writing

creative writing

#80

of 386 · 1411

LMArena · Maths

maths questions in chat

#81

of 373 · 1441

LMArena · Text

overall chat quality, judged by people

#87

of 388 · 1438

LMArena · WebDev

building web apps and front ends

#29

of 123 · 1581

LMArena · Coding

coding questions in chat

#92

of 383 · 1484

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-V4-Flash; 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 · 27 · per million tokens, in / out

S

StreamLake

$0.044 / $0.13 · fp8

cheapest

S

Sail Research

$0.019 / $0.42 · fp4

↗

D

DeepInfra

$0.060 / $0.18 · fp8

↗

M

Makora

$0.090 / $0.20

↗

R

Reka

$0.021 / $0.53

↗

D

DigitalOcean

$0.12 / $0.24

↗

B

BaseTen

$0.13 / $0.26 · fp8

↗

C

CoreWeave

$0.13 / $0.28 · fp8

↗

#### Run it yourself

🤗

Official weights

deepseek-ai/DeepSeek-V4-Flash-0731

↗

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

24 Apr 2026

Announcement

not linked yet

Release entry

DeepSeek-V4 preview (V4-Pro/V4-Flash)

Scored as

DeepSeek-V4-Flash

Artificial Analysis index

–

Output speed

–

Hugging Face

[deepseek-ai/DeepSeek-V4-Flash ↗](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash)

## DeepSeek releases · around this one

DeepSeekMath-V2

Open

27 NOV 2025

DeepSeek-V3.2

Open

1 DEC 2025

index 145

DeepSeek-V4-Flash (Apr 2026)

Open

24 APR 2026

index 145

DeepSeek-V4-Pro (Apr 2026)

Open

24 APR 2026

index 151

DeepSeek-V4-Flash

Open

31 JUL 2026

index 165

---
Source: https://themodelindex.org/models/deepseek-v4-flash/ · The Model Index · data as of 2026-10-01