Gemma 4 31B IT
by Modular · family gemma · listed Apr 2026RTVW
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
Current rates USD per 1M tokens
Input$0.25
Output$0.65
Cache read$0.08
Cache write—
Against the market
On the record
- Model id
google/gemma-4-31b-it- Context window
- 262K tokens
- Max output
- 33K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Jan 2025
- Released
- 2026-04-02
- Last updated
- 2026-04-02
- Provider docs
- docs.modular.com/models
Back of the envelope
≈
Also listed at
- Nvidiafree in · free out
- AMDfree in · free out
- Requestyfree in · free out
- DevPass (LLM Gateway)$0.10 in · $0.25 out
- FastRouter$0.10 in · $0.30 out
- Kilo Gateway$0.10 in · $0.34 out
- LLM Gateway$0.10 in · $0.25 out
- CoreWeave$0.10 in · $0.34 out
- Kenari$0.103 in · $0.406 out
- Lilac$0.11 in · $0.35 out
- OrcaRouter$0.13 in · $0.38 out
- NanoGPT$0.14 in · $0.40 out
- Vercel AI Gateway$0.14 in · $0.40 out
- Novita AI$0.14 in · $0.40 out
- Crusoe$0.14 in · $0.40 out