Gemma-4-31B-IT
by Nvidia · family gemma · listed Apr 2026RTVW
Open Gemma instruction model for efficient chat and self-hosted deployments
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
Cache write—
Against the market
On the record
- Model id
google/gemma-4-31b-it- Context window
- 256K tokens
- Max output
- 16K tokens
- Input modalities
- text, image, video
- 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.api.nvidia.com/nim/
Back of the envelope
≈
Also listed at
- Kenarifree in · free out
- Requestyfree in · free out
- Kilo Gateway$0.08 in · $0.35 out
- NanoGPT$0.10 in · $0.35 out
- OpenRouter$0.10 in · $0.34 out
- CrofAI$0.10 in · $0.30 out
- Weights & Biases$0.10 in · $0.34 out
- LLM Gateway$0.102 in · $0.297 out
- DevPass (LLM Gateway)$0.102 in · $0.297 out
- Lilac$0.11 in · $0.35 out
- OrcaRouter$0.13 in · $0.38 out
- Deep Infra$0.13 in · $0.38 out
- NEAR AI Cloud$0.13 in · $0.40 out
- FastRouter$0.13 in · $0.38 out
- SiliconFlow$0.13 in · $0.40 out