gemma-4-31b vs mistral-medium-3-5
- gemma-4-31b
- 2 advantages
- mistral-medium-3-5
- No edge in the figures
How to choose
gemma-4-31bReads imagesNo training on conversations
mistral-medium-3-5No edge in the figures
gemma-4-31b
By Google
mistral-medium-3-5
By Mistral AI
Where they differ
gemma-4-31bmistral-medium-3-5
On this site
98%102 callsAvailability, last 3 days—
96%193 testsAvailability, this week's tests—
2.1sAverage response this week—
FreeReference price per million output tokens$11.25
#8Place in this week's rankingUnranked
FreeReference price per million input tokens$2.25
The model itself
YesReads imagesNo
Not used for training.Conversations used for trainingUsed to train and improve the provider’s models.
Jan 2025Knowledge cutoffNot published
2 Apr 2026Released29 Apr 2026
FreeReference price per million cache-read tokens$2.25
Where they match
- Context length256K tokens
- Longest reply256K tokens
- Calls toolsYes
- Thinks before answeringYes
- Open weightsYes
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
gemma-4-31b against other models
mistral-medium-3-5 against other models
- vs gemini-4-hydrogen$11.25Reference price per million output tokens
- vs grok-4.7$9.00Reference price per million output tokens
- vs qwen3.8-max$9.00Reference price per million output tokens
- vs qwen3.8-2.4t-a95b$9.00Reference price per million output tokens
- vs gpt-6.1-terra$7.50Reference price per million output tokens
- vs kimi-k3.1-pro$15.00Reference price per million output tokens
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 Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.
