Using Gemma 3 on OpenRouter

Implementation guide · Gemma 3 · Google DeepMind

ServerlessOpen Weights

OpenRouter exposes Gemma 3 through model ID google/gemma-3-4b-it. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-15. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at OpenRouter and generate an API key.
  2. 2
    Use the OpenRouter SDK or REST API to call google/gemma-3-4b-it — see the documentation for request format.
  3. 3
    You'll be billed $0.04/1M input, $0.08/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See OpenRouter documentation for integration details.

Pricing on OpenRouter

TypePrice (per 1M)
Input tokens$0.04
Output tokens$0.08

Capabilities

Structured Outputs

About Gemma 3

Lightweight, state-of-the-art open model built from the same technology that powers Gemini models. Available for free local deployment via Hugging Face and other hosting providers.

Full model details →

Model Specs

Released2025-03-12
ArchitectureDecoder Only
Knowledge cutoff2025-01

More Models on OpenRouter

Gemma 3n 4B (free)Gemma 3 4B ITGemma 3 12BGemma 3 27B
All models on OpenRouter →

Also available on(2)

Google AI StudioFree/1MGCP Vertex AIFree/1M
Compare all providers →

Provider

OpenRouter

OpenRouter, Inc.

New York, NY, USA