Model APIs · Image generation
Run Flash Image 3.1 Lite by Google through one OpenAI-compatible endpoint. Pay per use against your GPU.ai balance — no instance to rent, no deployment to manage.
Live catalog rates, billed per use against your GPU.ai balance. No subscriptions, no minimums.
| Tier | Rate |
|---|---|
| Serverless | Per image: $0.069 |
Rates are read hourly from the live model catalog and metered per request.
Any OpenAI SDK works — set the base URL to https://api.gpu.ai/v1 and use your GPU.ai API key.
curl https://api.gpu.ai/v1/images/generations \
-H "Authorization: Bearer $GPUAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpuai/flash-image-3.1-lite",
"prompt": "A watercolor painting of a data center at sunrise"
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.gpu.ai/v1",
api_key="YOUR_GPUAI_API_KEY",
)
image = client.images.generate(
model="gpuai/flash-image-3.1-lite",
prompt="A watercolor painting of a data center at sunrise",
)
print(image.data[0].url)| Model id | gpuai/flash-image-3.1-lite |
| Modality | Image generation |
| Author | |
| Context window | — |
| Streaming | — |
| Aliases | — |
Flash Image 3.1 Lite on GPU.ai currently costs $0.069 (per image). There are no subscriptions or minimums — usage is billed against your GPU.ai balance as you go.
Yes. Point any OpenAI SDK at https://api.gpu.ai/v1 with a GPU.ai API key and request model "gpuai/flash-image-3.1-lite" — 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 GPU.ai balance.