← Models

DeepSeek V4 Pro 0813 vs DeepSeek V4.1 Flash 1017

Compare DeepSeek V4 Pro 0813 from DeepSeek and DeepSeek V4.1 Flash 1017 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 Pro 0813DeepSeekDeepSeek V4.1 Flash 1017
+ Add model · 2/4
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
30% off·Oct 19 – Oct 25 GMT+0
DeepSeek logo
DeepSeek V4.1 Flash 1017
DeepSeek · text, image → text

The official latest version of DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. API usage and pricing remain unchanged—you can still access the latest model using deepseek-flash.

Input$0.155$0.1085 /M
Output$0.62$0.434 /M
Cache read$0.0031$0.0022 /M
Details

Pricing & Specifications

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

DeepSeek V4 Pro 0813
DeepSeek V4.1 Flash 1017
Input /M
$0.6918
$0.155$0.1085−30%
Output /M
$2.0754
$0.62$0.434−30%
Cache read /M
$0.023
$0.0031$0.0022−30%
Context length
1,000,000
1,000,000
Max output
384,000
393,216
Time to First Token
0.5 s
1.7 s
Throughput
45.6 tok/s
125.7 tok/s
Modalities
text
textimage
Supported Parameters
toolsfunction callingstructured outputsthinking
API Formats
Released
August 13, 2026
October 17, 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-pro-0813deepseek-v4.1-flash-1017

Tokens / day

-

Requests / day

-

Performance Past 3 Days

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

deepseek-v4-pro-0813deepseek-v4.1-flash-1017

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

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

Text
deepseek-v4-pro-0813deepseek-v4.1-flash-1017
142014601500
Overall
14581475
Coding
15021502
Math
14451445
Hard prompts
14801480
Instruction following
14531453
Multi-turn
14761476
Creative writing
14441444
Longer query
14721472
Chinese
14941494
English
14671467
WebDev Arena
deepseek-v4-pro-0813deepseek-v4.1-flash-1017
14001460152015801640
Overall
14461619
React
14391439
HTML
14351435
Gaming
14491449
Simulations
14421442
Data analytics
14361436

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 V4.1 Flash 1017
$19$13.02 /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 Pro 0813, DeepSeek V4.1 Flash 1017?

DeepSeek V4.1 Flash 1017: $0.434/M output tokens; DeepSeek V4 Pro 0813: $2.0754/M. Use the cost calculator above to estimate your own workload.

Which responds faster?

DeepSeek V4 Pro 0813: 0.5s 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 Pro 0813 accepts 1,000,000 and DeepSeek V4.1 Flash 1017 accepts 1,000,000 input tokens. Maximum output per request is 384,000 tokens on DeepSeek V4 Pro 0813 and 393,216 tokens on DeepSeek V4.1 Flash 1017.

Which one generates tokens faster?

DeepSeek V4.1 Flash 1017 at 125.7 tok/s and DeepSeek V4 Pro 0813 at 45.6 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 Pro 0813 accepts text input and supports tool calling, function calling, structured outputs and thinking; DeepSeek V4.1 Flash 1017 accepts text and image input.

Can I call DeepSeek V4 Pro 0813 and DeepSeek V4.1 Flash 1017 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

Company

Terms & Policies