OpenRouter: Gemini 3 Pro (Preview, OR)
previewGemini 3 Pro (Preview, OR) is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.
Activity
Providers
Pricing
| Item | Price | Unit |
|---|---|---|
| Input | $2.00 | per 1M tokens |
| Output | $12.00 | per 1M tokens |
Performance
Reliability
Compare
Capabilities
- Model ID
- google-gemini-3-pro-preview
- Family
- gemini-3
- Status
- preview
- Knowledge
- -
- Released
- -
- API
- 2024-01-01
- Auth
- OPENROUTER_API_KEY
- Discovery
- dynamic
- Provider type
- meta
Quick Start
Endpoint
https://openrouter.ai/api/v1https://openrouter.ai/api/v1/chat/completionsgoogle-gemini-3-pro-previewOPENROUTER_API_KEYGemini 3 Pro (Preview, OR) FAQ
How much does the Gemini 3 Pro (Preview, OR) API cost?
Through OpenRouter, Gemini 3 Pro (Preview, OR) costs $2.00 per 1M input tokens and $12.00 per 1M output tokens.
What is the context window of Gemini 3 Pro (Preview, OR)?
Gemini 3 Pro (Preview, OR) accepts up to 1.1M tokens of context and returns up to 66K output tokens on OpenRouter.
Which providers offer Gemini 3 Pro (Preview, OR)?
Gemini 3 Pro (Preview, OR) is available from Google, OpenRouter and Vertex AI. Everstack can route between them with automatic fallback when one is unavailable.
What can Gemini 3 Pro (Preview, OR) do?
Gemini 3 Pro (Preview, OR) supports chat, function calling, image input and reasoning. It accepts text, image, audio, video and PDF input.
How do I call Gemini 3 Pro (Preview, OR) through Everstack?
Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @openrouter/google-gemini-3-pro-preview. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.
