Skip to content

GPT Image

OpenAI's image generation family. All models share one parameter set — GPT Image 2.5 adds two higher quality tiers on top of GPT Image 2. For editing existing images with these models, see GPT Image (Edits).

POST https://llm.siraya.ai/v1/images/generations

Supported Models

Model ID Description
gpt-image-2.5-flare Speed-optimized GPT Image 2.5. The default choice for most workloads.
gpt-image-2.5-sunburst Quality-optimized GPT Image 2.5, roughly 2x slower than Flare.
gpt-image-2 Previous generation. Same parameters, without the xhigh / max quality tiers.
Authorization string Required
Your API Key (e.g., `Bearer `).

Body

model string Required
The ID of the model to use (gpt-image-2.5-flare, gpt-image-2.5-sunburst, or gpt-image-2).
prompt string Required
A text description of the desired image.
n integer Default: 1
The number of images to generate (1-10).
size string Default: auto
The dimensions of the generated image. Any WIDTHxHEIGHT value is accepted as long as both sides are multiples of 16, the aspect ratio is between 1:3 and 3:1, and the size does not exceed 3840x2160 — e.g. 1024x1024, 1536x1024, 2048x1152, 3840x2160. Images are returned at the exact pixel size requested. Use auto to let the model pick.
quality string Default: auto
The quality of the generated image. Possible values: low, medium, high, auto. The GPT Image 2.5 models also accept xhigh and max.
background string Default: auto
The background type for the generated image. Possible values: transparent, opaque, auto. A transparent background requires output_format: png.
output_format string Default: png
The encoding of the returned image. Possible values: png, jpeg.
output_compression integer Default: 100
The compression level for the output image (0-100). Only valid with output_format: jpeg.
moderation string Default: auto
The content moderation level. Possible values: low, auto.
async boolean Default: false
When false, the request waits for generation to finish and returns the completed image. When true, it returns immediately with an image id while generation runs in the background. There is no status/poll endpoint for images — pass callbackUrl to receive the result. See Asynchronous generation.
callbackUrl string
Only used when async is true. A URL the router will POST to once generation completes (or fails). This is the only way to retrieve the result of an async image job.
extra_body object
Additional model-specific parameters passed directly to the provider. Unknown top-level fields are also automatically captured into this object. 
curl https://llm.siraya.ai/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
    "model": "gpt-image-2.5-flare",
    "n": 1,
    "prompt": "A child plays the guitar.",
    "size": "1536x1024",
    "quality": "high",
    "output_format": "png"
  }'

import requests

url = "https://llm.siraya.ai/v1/images/generations"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer <API_KEY>"
}
data = {
    "model": "gpt-image-2.5-flare",
    "n": 1,
    "prompt": "A child plays the guitar.",
    "size": "1536x1024",
    "quality": "high",
    "output_format": "png"
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Example Response

{
    "created": 1774716098,
    "data": [
        {
            "b64_json": "iVBORw0KGgoAAAANSUhEUgAABAAAAAQACAIAAADwf7zUAAAAg3..."
        }
    ]
}

Choosing a model

gpt-image-2.5-flare gpt-image-2.5-sunburst gpt-image-2
Optimized for Speed Quality —
Relative latency Baseline ~2x Flare —
quality tiers low–max low–max low–high
Best for Interactive and high-volume generation Hero images, print, final assets Existing integrations pinned to this model

Arbitrary pixel sizes (including 2K and 4K), transparent backgrounds, and jpeg output behave the same on every model in the family.