Gemma 3 4B
google/gemma-3-4b-it
- context
- 131K
- modalities
- text, image → text
- capabilities
- Vision, Structured output, Low cost
Overview
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
Providers
- Amazon BedrockView Amazon Bedrock
- DeepInfraView DeepInfra
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| Amazon Bedrock | $0.04 | $0.08 |
| DeepInfra | $0.05 | $0.10 |
Amazon Bedrock
- input / 1M
- $0.04
- output / 1M
- $0.08
DeepInfra
- input / 1M
- $0.05
- output / 1M
- $0.10
Use this model
through Nautili
Route requests to Gemma 3 4B through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.