model apis · image generation
Run Gemini 3 Pro Image by Google through one OpenAI-compatible endpoint. Pay per use against your deeprelay balance. No instance to rent, no deployment to manage.
Available nowLive catalog rates, billed per use against your deeprelay balance, no minimums. Gemini 3 Pro Image is priced per use rather than included in the $2.99-a-month flat plan.
| Tier | Rate |
|---|---|
| Serverless | Per image: $0.142 |
rates are read every few minutes from the live model catalog and metered per request
Any OpenAI SDK works: set the base URL to https://api.deeprelay.ai/v1 and use your deeprelay API key.
curl https://api.deeprelay.ai/v1/images/generations \
-H "Authorization: Bearer $DEEPRELAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deeprelay/gemini-3-pro-image",
"prompt": "A watercolor painting of a data center at sunrise"
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.deeprelay.ai/v1",
api_key="YOUR_DEEPRELAY_API_KEY",
)
image = client.images.generate(
model="deeprelay/gemini-3-pro-image",
prompt="A watercolor painting of a data center at sunrise",
)
print(image.data[0].url)| Model id | deeprelay/gemini-3-pro-image |
| Modality | Image generation |
| Author | |
| Context window | – |
| Streaming | – |
| Aliases | – |
| Flat plan | Not included: pay as you go |
faq
Gemini 3 Pro Image on deeprelay currently costs $0.142 (per image), billed against your deeprelay balance as you go. There are no minimums. It is priced per use rather than included in the $2.99-a-month flat plan, which covers a named set of models.
Yes. Point any OpenAI SDK at https://api.deeprelay.ai/v1 with a deeprelay API key and request model "deeprelay/gemini-3-pro-image". No proprietary client needed.
Generation models bill per output (per image, or per second of video) at the listed rate, metered per request against your deeprelay balance.