- Third-party
OpenAI's fastest high-quality everyday image generation model. It accepts text and image inputs and produces images with low, medium, high, xhigh, max, and auto quality settings.
| Model Info | |
|---|---|
| Terms and License | link ↗ |
| More information | link ↗ |
| Pricing |
|
const response = await env.AI.run(
'openai/gpt-image-2.5-flare',
{
prompt:
'A premium studio product photograph of a translucent orange mechanical keyboard on a cobalt blue acrylic pedestal, a few keys glowing amber, crisp reflections, bold geometric shadows, clean commercial art direction, no logos or readable words',
quality: 'high',
size: '1024x1024',
output_format: 'jpeg',
},
)
console.log(response)curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
--header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"model": "openai/gpt-image-2.5-flare",
"input": {
"prompt": "A premium studio product photograph of a translucent orange mechanical keyboard on a cobalt blue acrylic pedestal, a few keys glowing amber, crisp reflections, bold geometric shadows, clean commercial art direction, no logos or readable words",
"quality": "high",
"size": "1024x1024",
"output_format": "jpeg"
}
}'
{
"state": "Completed",
"result": {
"image": "https://examples.aig.cloudflare.com/openai/gpt-image-2.5-flare/commercial-product-scene.jpg"
},
"gatewayMetadata": {
"keySource": "Unified"
}
}Environmental Concept Frame — Generate a wide environmental concept frame
const response = await env.AI.run(
'openai/gpt-image-2.5-flare',
{
prompt:
'A wide establishing shot of a hidden mountain library carved into basalt cliffs, tiny figures crossing rope bridges, waterfalls disappearing into mist, late afternoon sun, grounded fantasy concept art with realistic scale',
quality: 'xhigh',
size: '1536x1024',
},
)
console.log(response)curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
--header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"model": "openai/gpt-image-2.5-flare",
"input": {
"prompt": "A wide establishing shot of a hidden mountain library carved into basalt cliffs, tiny figures crossing rope bridges, waterfalls disappearing into mist, late afternoon sun, grounded fantasy concept art with realistic scale",
"quality": "xhigh",
"size": "1536x1024"
}
}'
{
"state": "Completed",
"result": {
"image": "https://examples.aig.cloudflare.com/openai/gpt-image-2.5-flare/environmental-concept-frame.png"
},
"gatewayMetadata": {
"keySource": "Unified"
}
}Poster Reference Edit — Transform a reference sketch into a finished illustration
const response = await env.AI.run(
'openai/gpt-image-2.5-flare',
{
prompt:
'Reimagine the reference as a vibrant risograph poster for a fictional night market. Keep the central market stall silhouette and hanging lantern arrangement, add layered coral, teal, and navy ink textures, imperfect registration, and a lively crowd rendered as abstract shapes',
images: [
'data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAYAAABzenr0AAAAnklEQVR42u2XQRLAIAgD8/839i/26qFCACm0ozPe1KwcQsAoXvgcAABxpwFowl4QWITHxW0LCBhxVngF4gKIirMQyBRnIJAtrkE8AuwWnyFEgKzfS1UA+3sWTju3BGAu7gKYIfBW+Q/AAQgBeMCkt1wVsLZjcwUYG2Z9wGLHZitWk1DEisubUYt2XB5IWkSyFqG0RSxvMZi0Gc1+Ox3fm00ZJ5mGVtkAAAAASUVORK5CYII=',
],
quality: 'medium',
output_format: 'png',
},
)
console.log(response)curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
--header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"model": "openai/gpt-image-2.5-flare",
"input": {
"prompt": "Reimagine the reference as a vibrant risograph poster for a fictional night market. Keep the central market stall silhouette and hanging lantern arrangement, add layered coral, teal, and navy ink textures, imperfect registration, and a lively crowd rendered as abstract shapes",
"images": [
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAYAAABzenr0AAAAnklEQVR42u2XQRLAIAgD8/839i/26qFCACm0ozPe1KwcQsAoXvgcAABxpwFowl4QWITHxW0LCBhxVngF4gKIirMQyBRnIJAtrkE8AuwWnyFEgKzfS1UA+3sWTju3BGAu7gKYIfBW+Q/AAQgBeMCkt1wVsLZjcwUYG2Z9wGLHZitWk1DEisubUYt2XB5IWkSyFqG0RSxvMZi0Gc1+Ox3fm00ZJ5mGVtkAAAAASUVORK5CYII="
],
"quality": "medium",
"output_format": "png"
}
}'
{
"state": "Completed",
"result": {
"image": "https://examples.aig.cloudflare.com/openai/gpt-image-2.5-flare/poster-reference-edit.png"
},
"gatewayMetadata": {
"keySource": "Unified"
}
}prompt
stringrequiredText prompt describing the image to generate or edit▶images[]
arraymaxItems: 16Input images for image editing, 1-16 entries. Each entry is base64-encoded (raw string or data:image/{png|jpeg|webp};base64,... URI).quality
stringenum: low, medium, high, xhigh, max, autoQuality of the generated imagesize
stringenum: 1024x1024, 1024x1536, 1536x1024, autoSize of the generated imagebackground
stringenum: transparent, opaque, autoBackground transparency settingoutput_format
stringenum: png, webp, jpegOutput format for the generated imageimage
stringformat: uriURL to the generated image