Image Generation API

Supported Models

  • openai/gpt-image-1

  • openai/dall-e-2

  • openai/dall-e-3

Parameters

Parameter
Type
Required
Default
Supported
Model Notes

n

integer or null

Optional

1

1–10

Only n=1 is supported for dall-e-3.

output_format

string or null

Optional

png

png, jpeg, webp

Only supported for gpt-image-1.

quality

string or null

Optional

auto

auto, high, medium, low, hd, standard

gpt-image-1: auto, high, medium, low dall-e-3: auto, hd, standard dall-e-2: standard only

size

string or null

Optional

auto

auto, 1024x1024, 1536x1024, 1024x1536, 256x256, 512x512, 1792x1024, 1024x1792

gpt-image-1: auto, 1024x1024, 1536x1024, 1024x1536 dall-e-2: 256x256, 512x512, 1024x1024 dall-e-3: 1024x1024, 1792x1024, 1024x1792

background

string or null

Optional

auto

transparent, opaque, auto

Only supported for gpt-image-1. If set to transparent, output_format must be png or webp. auto lets the model decide the best background.

OpenAI Compatible Image Request Format

FastRouter offers an OpenAI-compatible request schema.

import base64
import openai
client = openai.OpenAI(
    api_key="API-KEY",
    base_url="https://go.fastrouter.ai/api/v1" 
)

img = client.images.generate(
    model="openai/gpt-image-1",
    prompt="A cute baby sea otter",
    n=1,
    size="1024x1024"
)
image_base64 = img.data[0].b64_json
image_bytes = base64.b64decode(image_base64)

# Save the image to a file
with open("otter.png", "wb") as f:
    f.write(image_bytes)

Calling FastRouter Directly

curl --location 'https://go.fastrouter.ai/api/v1/images/generations' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer API-KEY' \
--data '{
	"model": "openai/dall-e-3",
	"prompt": "A group of children playing cricket",
	"n": 1,
	"size": "1024x1024"
}'

Last updated