ModelBeat
Models/DeepSeek V4 Flash 0731
All models
D

DeepSeek: DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731

DeepSeek V4 Flash 0731 is DeepSeek’s open-weights AI model, released Jul 31, 2026. It costs $0.04/M input and $0.16/M output tokens, and handles a 1.3M-token context window. Its strongest use case is coding, where it ranks in the 76th percentile of the models Model Beat tracks.

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.

Context
1.3M
Input
$0.04 / 1M
Output
$0.16 / 1M
Released
Jul 31, 2026
Modalities
texttext
Strongest atCoding top 24%Math top 32%

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where DeepSeek V4 Flash 0731 lands among all models tracked on Model Beat.

67.0
Intelligence Index
Epoch AI
67th percentile of tracked models
76.0
Coding Index
Epoch AI
76th percentile of tracked models

Reasoning

7 evals
ARC-AGI89.0%

Abstract visual reasoning

ARC-AGI-261.4%

Harder abstract reasoning

GPQA Diamond91.0%

Graduate-level scientific reasoning

Humanity's Last Exam38.6%

Frontier of human expert knowledge

SimpleBench61.1%

Common-sense trick questions

SimpleQA Verified33.6%

Factual accuracy & hallucination

WeirdML63.0%

Novel ML problem-solving

Coding

2 evals
SciCode50.3%

Scientific research coding

WebDev Arena1579

Human-rated web development

Math

1 evals
AIME 2024/202594.4%

Olympiad-qualifier math

In the news

3

Changelog

12
  • DeepSeek V4 Flash 0731: cheapest credible provider via OpenInference now $0.04 per 1M input tokens (was $0.05, -20%)cheapest provider · Sep 15, 2026
  • DeepSeek V4 Flash 0731: cheapest credible provider via OpenInference now $0.05 per 1M input tokens (was $0.03, +67%)cheapest provider · Sep 4, 2026
  • DeepSeek V4 Flash 0731: cheapest credible provider via OpenInference now $0.16 per 1M output tokens (was $0.18, -11%)cheapest provider · Sep 2, 2026
  • DeepSeek V4 Flash 0731: vendor list price raised from $0.14 to $0.22 per 1M input tokens (+57%)list price · Aug 31, 2026
  • DeepSeek V4 Flash 0731: vendor list price raised from $0.28 to $0.66 per 1M output tokens (+136%)list price · Aug 31, 2026
  • DeepSeek V4 Flash 0731: cheapest credible provider via OpenInference now $0.03 per 1M input tokens (was $0.08, -62%)cheapest provider · Aug 31, 2026
  • DeepSeek V4 Flash 0731: cheapest credible provider via DeepInfra now $0.18 per 1M output tokens (was $0.26, -31%)cheapest provider · Aug 17, 2026
  • DeepSeek V4 Flash 0731: context window changed from 1,048,576 to 1,310,720 tokenscontext · Aug 17, 2026
  • DeepSeek V4 Flash 0731: cheapest credible provider via DigitalOcean now $0.08 per 1M input tokens (was $0.13, -38%)cheapest provider · Aug 10, 2026
  • DeepSeek V4 Flash 0731: cheapest credible provider via BaseTen now $0.26 per 1M output tokens (was $0.28, -7%)cheapest provider · Aug 7, 2026
  • DeepSeek V4 Flash 0731: cheapest credible provider via BaseTen now $0.13 per 1M input tokens (was $0.14, -7%)cheapest provider · Aug 7, 2026
  • DeepSeek V4 Flash 0731 (DeepSeek) added to the tracker: $0.14/$0.28 per 1M, 1M context.tracked · Jul 31, 2026

Compare DeepSeek V4 Flash 0731 with

Frequently asked questions

What is DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.

Who created DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 is an AI model developed by DeepSeek, part of the DeepSeek family, released Jul 31, 2026.

How much does DeepSeek V4 Flash 0731 cost?

DeepSeek V4 Flash 0731 is served from $0.04 per million input tokens and $0.16 per million output tokens (cheapest credible provider on OpenRouter: OpenInference).

What is DeepSeek V4 Flash 0731's context window?

DeepSeek V4 Flash 0731 supports a context window of up to 1.3M tokens.

How does DeepSeek V4 Flash 0731 perform on benchmarks?

On standardized evaluations tracked by Epoch AI, DeepSeek V4 Flash 0731 scores 1579 on WebDev Arena, 91.0% on GPQA Diamond, 38.6% on Humanity's Last Exam.

Is DeepSeek V4 Flash 0731 open source?

DeepSeek V4 Flash 0731 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 Sep 15, 2026.