Image model by Google
gemini-3.1-flash-image API
model: gemini-3.1-flash-image
Call gemini-3.1-flash-image with your KeelRouter API key, the same key you use for every other model. From $0.045 per image, paid per call from a prepaid balance. Failed calls are free.
Pricing
| Option | Price |
|---|---|
| 512 | $0.046 per image |
| 1K | $0.045 per image |
| 2K | $0.06 per image |
| 4K | $0.10 per image |
Call it
Async: POST /v1/images/generations returns a taskId; poll the same path with ?task_id= or pass a callback_url.
curl https://api.keelrouter.com/v1/images/generations \
-H "Authorization: Bearer $KEELROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.1-flash-image",
"prompt": "A lighthouse at dawn, watercolor",
"resolution": "512"
}'Parameters
| Name | Type | Notes |
|---|---|---|
| model | string | Required. gemini-3.1-flash-image |
| prompt | string | Required. |
| image_url | string | |
| image_urls | array | |
| aspect_ratio | string | One of auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3. Default auto. |
| resolution | string | One of 512, 1k, 2k, 4k. Default 1k. |
| callback_url | string | Optional https URL; we POST the result when the task ends |
FAQ
- How much does the gemini-3.1-flash-image API cost on KeelRouter?
- From $0.045 per image. You pay per call from a prepaid USD balance; failed calls are not charged.
- How do I call gemini-3.1-flash-image?
- POST to /v1/images/generations with model "gemini-3.1-flash-image". You get a taskId back; poll the same endpoint with ?task_id= or pass a callback_url.
- Is this the official gemini-3.1-flash-image API?
- No. KeelRouter is an independent API gateway. Requests run on gemini-3.1-flash-image through our upstream providers, and the image model keeps its own safety filters.
- How long are results kept?
- Result files are kept for 30 days, then deleted. Download what you want to keep.
More from Google
KeelRouter is an independent service and is not affiliated with Google. gemini-3.1-flash-image is a trademark of its owner, used here only to name the model a request runs on.