Mistral AI · text model

Mistral Large 4

#21 of 31 text models on overall (provisional). $3.71 per 1,000 support replies at list price.

Price checked 25 Oct 2026 via vendor
key_facts.txt
Released
6 Oct 2026
Context window
1M tokens
Longest reply
262K tokens
Open weights
No
Reasoning mode
Yes
Tool use
Yes
Reads
text, image, pdf
Writes
text
Knowledge cutoff
–
scores.txt
Overall37
Writing34
Support46
Coding55
Value30
Provisional, 0 to 100 among the text models we track, from Arena and Epoch AI. How we score.

Prices and where to run it

ProviderRegionInput per 1MOutput per 1MCached inputData retentionChecked
mistralglobal$1.36$4.18$0.14Not checked25 Oct 2026, vendor
openrouterglobal$1.36$4.18$0.14Not checked25 Oct 2026, OpenRouter

Price history and a CSV download arrive with the open price dataset.

Benchmarks behind the scores

MeasureFigureRun dateSource
Epoch Capabilities Index15025 Oct 2026Epoch AI
Arena text, coding1479.922 Oct 2026Arena
Arena text, creative writing1363.822 Oct 2026Arena
Arena text, instruction following1423.722 Oct 2026Arena
Arena text, multi-turn1440.722 Oct 2026Arena
Arena text, overall1431.922 Oct 2026Arena
Arena WebDev1544.823 Oct 2026Arena
call_it.sh
Call it through OpenRouter
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mistralai/mistral-large-4-0", "messages": [{"role": "user", "content": "Hello"}]}'
next.txt
Compare and switchAlternatives to Mistral Large 4 →Mistral Large 4 vs Grok 4.7 →Work out your monthly cost →
alerts.txt
Model Menu will email you about this, plus the Friday letter. One click unsubscribes. We never sell or share your address.