Gemma 3 4B IT
by Nvidia · family gemma · listed Mar 2025TVW
Open multimodal Gemma instruction model for efficient text generation and image understanding
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
Cache write—
Against the market
On the record
- Model id
google/gemma-3-4b-it- Context window
- 131K tokens
- Max output
- 16K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Aug 2024
- Released
- 2025-03-12
- Last updated
- 2025-03-12
- Provider docs
- docs.api.nvidia.com/nim/
Back of the envelope
≈
Also listed at
- Kilo Gateway$0.04 in · $0.05 out
- Merge Gateway$0.04 in · $0.08 out
- Eden AI$0.05 in · $0.10 out
- OpenRouter$0.05 in · $0.10 out
- Hugging Face$0.05 in · $0.10 out
- Deep Infra$0.05 in · $0.10 out
- AI/ML API$0.0529 in · $0.106 out
- NanoGPT$0.201 in · $0.201 out