Google: Gemini 3 Pro (Preview)
previewGemini 3 Pro (Preview) 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 |
| Cache read | $0.20 | per 1M tokens |
Performance
Reliability
Compare
Capabilities
- Model ID
- gemini-3-pro-preview
- Family
- gemini-3
- Status
- preview
- Knowledge
- -
- Released
- Nov 18, 2025
- API
- 2024-01-01
- Auth
- GOOGLE_API_KEY
- Discovery
- static
- Provider type
- static
Quick Start
Endpoint
https://generativelanguage.googleapis.com/v1https://generativelanguage.googleapis.com/v1/chat/completionsgemini-3-pro-previewGOOGLE_API_KEYGemini 3 Pro (Preview) FAQ
How much does the Gemini 3 Pro (Preview) API cost?
Through Google, Gemini 3 Pro (Preview) costs $2.00 per 1M input tokens and $12.00 per 1M output tokens.
What is the context window of Gemini 3 Pro (Preview)?
Gemini 3 Pro (Preview) accepts up to 1M tokens of context and returns up to 64K output tokens on Google.
Which providers offer Gemini 3 Pro (Preview)?
Gemini 3 Pro (Preview) 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) do?
Gemini 3 Pro (Preview) supports chat, image input, function calling and reasoning. It accepts text, image, video, audio and PDF input.
How do I call Gemini 3 Pro (Preview) through Everstack?
Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @google/gemini-3-pro-preview. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.
