Google · text model

Gemma 4 31B IT

#27 of 31 text models on overall (provisional). $0.46 per 1,000 support replies at list price.

Price checked 25 Oct 2026 via models.dev
key_facts.txt
Released
2 Apr 2026
Context window
262K tokens
Longest reply
16K tokens
Open weights
Yes
Reasoning mode
Yes
Tool use
Yes
Reads
image, text, video
Writes
text
Knowledge cutoff
2025-01
scores.txt
Overall28
Writing50
Support51
Coding30
Value32
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
openrouterglobal$0.20$0.40–Not checked25 Oct 2026, models.dev

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

Benchmarks behind the scores

MeasureFigureRun dateSource
Epoch Capabilities Index14325 Oct 2026Epoch AI
Arena text, coding1459.222 Oct 2026Arena
Arena text, creative writing141622 Oct 2026Arena
Arena text, instruction following1433.622 Oct 2026Arena
Arena text, multi-turn1451.922 Oct 2026Arena
Arena text, overall1442.922 Oct 2026Arena
Arena WebDev1368.423 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": "google/gemma-4-31b-it", "messages": [{"role": "user", "content": "Hello"}]}'
next.txt
Compare and switchAlternatives to Gemma 4 31B IT →Gemma 4 31B IT vs Nemotron 3.5 Super VL →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.