DeepSeek V4 Pro 0813 vs DeepSeek V4.1 Flash 1017

$0.36 / task
Wins 0 of 4 benchmarks
$0.26 / task
Wins 3 of 4 benchmarks
DeepSeek V4 Pro 081310.6
DeepSeek V4.1 Flash 101743.3
DeepSeek V4 Pro 08131.5
DeepSeek V4.1 Flash 101733.8
DeepSeek V4 Pro 081334.9
DeepSeek V4.1 Flash 101766.6
DeepSeek V4 Pro 0813—
DeepSeek V4.1 Flash 101780.6

Specs

SpecDeepSeek V4 Pro 0813DeepSeek V4.1 Flash 1017
Input, per 1M$1.32$0.30
Output, per 1M$3.96$1.20
Cost per task?$0.36$0.26
Speed, tok/s104169
Context1M1M
WeightsOpenOpen
ReleasedAug 2026Oct 2026
Memory (4-bit)990 GB458 GB
LicenceMITMIT
Commercial useAllowedAllowed
See images—✓
Read PDFs——
Hear audio——
Watch video——
Call tools✓✓
Force a tool call✓✓
Return strict JSON✓✓
Search the web??
Run code??
Use a computer??

What breaks when you switch

DeepSeek V4 Pro 0813 → DeepSeek V4.1 Flash 1017
Pass back reasoning_content · Chat Completions›

With thinking and tools, return all prior reasoning_content even on turns without tool calls or the API returns HTTP 400.

Disable thinking mode first · Chat Completions›

Required and named tool choices return HTTP 400 in thinking mode; disable thinking first.

Parameters have no effect›

In thinking mode, temperature, presence_penalty and frequency_penalty have no effect.

Values below 0.95›

Flash clamps top_p below 0.95 to 0.95 while thinking and ignores it in non-thinking mode, using 1.0.

Stateless API · Responses›

Responses does not support previous_response_id or conversation; preserve conversation history in your client.

DeepSeek V4.1 Flash 1017 → DeepSeek V4 Pro 0813
Memory (4-bit): 458 GB → 990 GB
No image input
Pass back reasoning_content · Chat Completions›

With thinking and tools, return all prior reasoning_content even on turns without tool calls or the API returns HTTP 400.

Disable thinking mode first · Chat Completions›

Required and named tool choices return HTTP 400 in thinking mode; disable thinking first.

Parameters have no effect›

In thinking mode, temperature, presence_penalty and frequency_penalty have no effect.

top_p value is ignored›

In thinking mode, top_p is fixed at 0.95 with tools and 1.0 otherwise; in non-thinking mode it takes effect.

Stateless API · Responses›

Responses does not support previous_response_id or conversation; preserve conversation history in your client.