← Models

DeepSeek V4 Flash 0731 vs DeepSeek V4 Pro 0813

Compare DeepSeek V4 Flash 0731 from DeepSeek and DeepSeek V4 Pro 0813 from DeepSeek on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.

DeepSeekDeepSeek V4 Flash 0731DeepSeekDeepSeek V4 Pro 0813
+ Add model · 2/4
DeepSeek logo
DeepSeek V4 Flash 0731
DeepSeek · text → text

DeepSeek-V4-Flash-0731(deepseek-v4-flash-0731) is an open-source MoE large language model developed by the Chinese AI company DeepSeek, with support for a million-token context window. It is designed for coding, complex reasoning, tool use, agentic workflows, and long-document processing. Its advantages include strong performance with fewer active parameters and improved efficiency through DSpark speculative decoding. Compared with DeepSeek V4-Flash Preview, it offers significantly stronger coding and agent capabilities, while outperforming DeepSeek V4-Pro Preview on several benchmarks with fewer active parameters.

Input$0.142 /M
Output$0.284 /M
Cache read$0.0284 /M
Details
DeepSeek logo
DeepSeek V4 Pro 0813
DeepSeek · text → text

DeepSeek V4 Pro 0813 is DeepSeek’s high-performance general-purpose reasoning and agent model, designed for complex reasoning, coding, long-document analysis, and agentic workflows. It supports thinking and non-thinking modes, a 1M-token context window, up to 384K output, tool calling, and the Responses API. Compared with V4 Flash 0731, Pro prioritizes capability on complex tasks, while Flash focuses on speed, cost efficiency, and high concurrency.

Input$0.6918 /M
Output$2.0754 /M
Cache read$0.023 /M
Details

Pricing & Specifications

Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.

DeepSeek V4 Flash 0731
DeepSeek V4 Pro 0813
Input /M
$0.142
$0.6918
Output /M
$0.284
$2.0754
Cache read /M
$0.0284
$0.023
Context length
1,000,000
1,000,000
Max output
384,000
384,000
Time to First Token
0.6 s
1.5 s
Throughput
82.9 tok/s
37.2 tok/s
Modalities
text
text
Supported Parameters
toolsfunction callingstructured outputsthinking
toolsfunction callingstructured outputsthinking
API Formats
chat_completions · claude_api
Released
July 31, 2026
August 13, 2026

Promotional prices show the discounted rate; see each model page for promotion windows.

Activity Past 30 Days

Daily traffic served through AIHubMix — how demand for each model is trending.

deepseek-v4-flash-0731deepseek-v4-pro-0813

Tokens / day

-

Requests / day

-

Performance Past 3 Days

Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.

deepseek-v4-flash-0731deepseek-v4-pro-0813

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.

Text
deepseek-v4-flash-0731deepseek-v4-pro-0813
1380142014601500
Overall
14361458
Coding
14831502
Math
14261445
Hard prompts
14591480
Instruction following
14281453
Multi-turn
14521476
Creative writing
14081444
Longer query
14481472
Chinese
14731494
English
14451467

Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.

Cost calculator

Estimate your monthly bill for the same workload on each model.

DeepSeek V4 Flash 0731
$12.78 /mo
DeepSeek V4 Pro 0813
$72.64 /mo

Monthly = daily × 30. Discounted rates applied where a promotion is active.

FAQ

Which is cheaper: DeepSeek V4 Flash 0731, DeepSeek V4 Pro 0813?

DeepSeek V4 Flash 0731: $0.284/M output tokens; DeepSeek V4 Pro 0813: $2.0754/M. Use the cost calculator above to estimate your own workload.

How do their coding arena scores compare?

DeepSeek V4 Pro 0813: 1502; DeepSeek V4 Flash 0731: 1483 (LMArena coding leaderboard).

Which responds faster?

DeepSeek V4 Flash 0731: 0.6s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.

How large is each context window?

DeepSeek V4 Flash 0731 accepts 1,000,000 and DeepSeek V4 Pro 0813 accepts 1,000,000 input tokens. Maximum output per request is 384,000 tokens on DeepSeek V4 Flash 0731 and 384,000 tokens on DeepSeek V4 Pro 0813.

Which one generates tokens faster?

DeepSeek V4 Flash 0731 at 82.9 tok/s and DeepSeek V4 Pro 0813 at 37.2 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.

What inputs and capabilities does each model support?

DeepSeek V4 Flash 0731 accepts text input and supports tool calling, function calling, structured outputs and thinking; DeepSeek V4 Pro 0813 accepts text input and supports tool calling, function calling, structured outputs and thinking.

Can I call DeepSeek V4 Flash 0731 and DeepSeek V4 Pro 0813 with the same API key?

Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.

Popular comparisons

Related model match-ups readers also look at.

Kimi K3vsQwen3.8 Max PreviewClaude Opus 5vsGPT 5.6 LunaClaude Opus 5vsClaude Sonnet 5Gemini 3.1 Pro PreviewvsGPT 5.5GLM 5.2vsKimi K3Gemini 3.6 FlashvsQwen3.8 MaxDeepSeek V4 FlashvsGLM 5.2Claude Opus 5vsGrok 4.5

© 2023 - 2026 AIHubMix, LLC

Product

Developer

Connect

Terms & Policies