Gemma 4 31B Instruct
by Berget.AI · family gemma · listed Apr 2026RTVW
Open Gemma instruction model for efficient chat and self-hosted deployments
Current rates USD per 1M tokens
Input$0.28
Output$0.561
Cache read—
Cache write—
Against the market
On the record
- Model id
google/gemma-4-31B-it- Context window
- 128K tokens
- Max output
- 8K tokens
- Input modalities
- audio, image, text, video
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Dec 2025
- Released
- 2026-04-02
- Last updated
- 2026-04-02
- Provider docs
- api.berget.ai
Back of the envelope
≈
Also listed at
- Nvidiafree in · free out
- Googlefree in · free out
- Requestyfree in · free out
- AMDfree in · free out
- Adaption$0.09 in · $0.34 out
- CoreWeave$0.10 in · $0.34 out
- Kilo Gateway$0.10 in · $0.34 out
- DevPass (LLM Gateway)$0.10 in · $0.25 out
- FastRouter$0.10 in · $0.30 out
- LLM Gateway$0.10 in · $0.25 out
- NanoGPT$0.11 in · $0.33 out
- Doubleword$0.12 in · $0.35 out
- OrcaRouter$0.13 in · $0.38 out
- Vercel AI Gateway$0.14 in · $0.40 out
- Friendli$0.14 in · $0.40 out