onomeoonomeoBeta

deepseek-v4-pro vs mistral-small-3.1

deepseek-v4-pro
3 advantages
mistral-small-3.1
1 advantage

How to choose

deepseek-v4-proLonger context: 1M tokensThinks before answeringOpen weights
mistral-small-3.1Reads images

deepseek-v4-pro

By DeepSeek

mistral-small-3.1

By Mistral AINew in the last two weeks

Where they differ

deepseek-v4-promistral-small-3.1
On this site
—Availability, last 3 days99%102 calls
—Availability, this week's tests98%183 tests
—Average response this week9.2s
$5.75Reference price per million output tokensFree
UnrankedPlace in this week's ranking#6
$2.86Reference price per million input tokensFree
The model itself
1M tokensContext length128K tokens
384K tokensLongest reply32K tokens
NoReads imagesYes
YesThinks before answeringNo
Used to train and improve the provider’s models.Conversations used for trainingThe provider does not say.
May 2025Knowledge cutoffSep 2024
24 Apr 2026Released1 Mar 2025
YesOpen weightsNo
$0.24Reference price per million cache-read tokensFree

Where they match

  • Calls toolsYes

Availability over 3 days counts every call made through the site; this week's availability counts every call over the last 7 days, scheduled tests included, and response time comes from the site's own scheduled tests. Models marked as free are counted in calls; paid models are charged by usage, in US dollars.

Compare next

Figures come from real calls made through this site. Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.