Inference
Google Gemma 3
Canonical ID:
inference/google/gemma-3
Open Gemma instruction model for efficient chat and self-hosted deployments
Overview
Pricing and Limits
Token pricing
- Input
- $0.15/1M
- Output
- $0.3/1M
- Cached input
- N/A
Context and output
- Context window
- 125,000
- Max output tokens
- 4,096
- Qualified ID
- inference/google/gemma-3
Model Summary
Google Gemma 3 is a model listing in the Inference provider catalog. It is categorized under the gemma-3 family.
The model supports text, image modalities across input/output paths. Reported context capacity is 125,000. Pricing is listed at $0.15/1M input and $0.3/1M output.
More From Inference
Related models from the same provider catalog.
Inference
Llama 3.1 8B Instruct
inference/meta/llama-3.1-8b-instruct
Inference
Llama 3.2 11B Vision Instruct
inference/meta/llama-3.2-11b-vision-instruct
Inference
Llama 3.2 1B Instruct
inference/meta/llama-3.2-1b-instruct
Inference
Llama 3.2 3B Instruct
inference/meta/llama-3.2-3b-instruct
Inference
Mistral Nemo 12B Instruct
inference/mistral/mistral-nemo-12b-instruct
Inference
Osmosis Structure 0.6B
inference/osmosis/osmosis-structure-0.6b
Inference
Qwen 2.5 7B Vision Instruct
inference/qwen/qwen-2.5-7b-vision-instruct
Inference
Qwen 3 Embedding 4B
inference/qwen/qwen3-embedding-4b