Provider logo

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731
Provider logo

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731

DeepSeek V4 Flash 0731 is a re-post-trained Mixture-of-Experts model with a 1M-token context window, built for coding, reasoning, and agent workflows.

Added Jul 31, 2026

Model weights

Context Window

1.0M

Max Output

131.1K

Input Price (Auto)

$0.15/1M

Output Price (Auto)

$0.29/1M

Cache Read (Auto)

$0.015/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Design Arena.

Best Category

UI Component

Best Elo

1269

Best Rank Percentile

Top 23%

Ranking Distribution

6,900 battles

60%

45%

30%

15%

0%

10.8%

First

35.5%

Second

39.1%

Third

14.5%

Fourth

Category Performance

Elo
Rank
3DTop 27%Data VizTop 50%Game DevTop 24%UITop 23%WebsiteTop 24%

Models Arena

UI Component

Top 23%

1269

Elo

47.9%

Win

230.8s

Avg Time

#35

Rank

3D

Top 27%

1267

Elo

51.5%

Win

247.4s

Avg Time

#38

Rank

Game Development

Top 24%

1257

Elo

47.1%

Win

265.3s

Avg Time

#37

Rank

Website

Top 24%

1252

Elo

47.5%

Win

227.7s

Avg Time

#41

Rank

Data Visualization

Top 50%

1187

Elo

39.1%

Win

239.3s

Avg Time

#75

Rank

Updated Aug 25, 2026, 9:51 AM · Matched as Deepseek V4 Flash 0731

Design Arena

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…

Compare DeepSeek V4 Flash 0731 with similar models from the same provider or model family.

DeepSeek V4 Flash 0731 (Thinking)

deepseek/deepseek-v4-flash-0731:thinking

DeepSeek V4 Flash 0731 Thinking enables reasoning by default on the re-post-trained Mixture-of-Experts model with a 1M-token context window, built for coding, reasoning, and agent workflows.

DeepSeek V4 Flash Latest

deepseek/deepseek-v4-flash-latest

Compatibility alias that routes to the newest dated DeepSeek V4 Flash release. Currently uses Fireworks first for DeepSeek V4 Flash 0731, with automatic failover when needed. ⚠️ Privacy and logging guarantees are limited.

DeepSeek V4 Flash

deepseek/deepseek-v4-flash

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with a 1M-token context window, built for fast inference, high-throughput workloads, reasoning, coding, and agent workflows.

DeepSeek V4 Flash (Thinking)

deepseek/deepseek-v4-flash:thinking

DeepSeek V4 Flash Thinking enables DeepSeek's reasoning mode on the efficiency-optimized Mixture-of-Experts model with a 1M-token context window, built for fast inference, high-throughput workloads, reasoning, coding, and agent workflows.

DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813

DeepSeek V4 Pro 0813 is the general-availability release of DeepSeek V4 Pro, built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. DeepSeek reports strong gains over the preview and scores above Opus 4.8 on Terminal Bench 2.1, Cybergym, DeepSWE, and AutomationBench. It supports a 1M-token context window.

DeepSeek V4 Pro 0813 Thinking

deepseek/deepseek-v4-pro-0813:thinking

DeepSeek V4 Pro 0813 Thinking enables reasoning by default on the general-availability release of DeepSeek V4 Pro, built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. DeepSeek reports strong gains over the preview and scores above Opus 4.8 on Terminal Bench 2.1, Cybergym, DeepSWE, and AutomationBench. It supports a 1M-token context window.