Googlegemini-3-pro-image-preview
Gemini 3 Pro Image (Preview)
Google's most capable image model, up to 4K.
Gemini 3 Pro Image generates and edits images from a prompt, with 1K, 2K, and 4K output. Billed per generated image, so the price is the price whatever the prompt looks like.
- High-fidelity images
- 4K output
- Image editing
Model details
- Context window
- 66K tokens
- Max output
- 33K tokens
- Input
- Text, images
- Output
- Text, images
- Capabilities
- Vision, Streaming, JSON output
- Interfaces
- OpenAI-style Image Generation
Pricing
What each generation costs. The Inferray price is what you are charged — no gateway fee is added on top of it.
| Resolution | List price | You pay |
|---|---|---|
| 1K | $0.13 | $0.11 |
| 2K | $0.13 | $0.11 |
| 4K | $0.24 | $0.20 |
Why teams pick it
- Generates and edits at up to 4K
- Priced per image, not per prompt length
- Reads reference images as input
Call Gemini 3 Pro Image (Preview)
Gemini 3 Pro Image (Preview) answers on the API below — pick the one your code already speaks and just swap in your Inferray key.
/v1/images/generationsOpenAI-style Image Generation · openai SDK or plain HTTP
curl https://api.inferray.com/v1/images/generations \
-H "Authorization: Bearer inferray_..." \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3-pro-image-preview",
"prompt": "a quartz crystal on a workbench",
"n": 1
}'