Create an image - CometAPI Documentation

POST

images

generations

curl https://api.cometapi.com/v1/images/generations \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A paper boat floating on calm water at sunrise.",
    "quality": "low",
    "size": "1024x1024",
    "output_format": "jpeg"
  }'

{
  "created": 1781075000,
  "background": "opaque",
  "output_format": "jpeg",
  "quality": "low",
  "size": "1024x1024",
  "usage": {
    "input_tokens": 13,
    "input_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 13
    },
    "output_tokens": 196,
    "output_tokens_details": {
      "image_tokens": 196,
      "text_tokens": 0
    },
    "total_tokens": 209
  },
  "data": [
    {
      "b64_json": "/9j/4AAQSkZJRgABAQAAAQABAAD..."
    }
  ]
}

Use this route to create images from text with OpenAI-compatible request shapes on CometAPI.

Official reference

Read the OpenAI image generation guide before you rely on model-specific controls such as background, output_compression, streaming, or future GPT image options.
Use the OpenAI Create image reference for the current parameter list.

Choose a model first

Use a GPT image model such as gpt-image-2 for text-to-image requests with controls like output_format, quality, or background
Use gpt-image-2.5-sunburst or gpt-image-2.5-flare when you need transparent backgrounds or the xhigh and max quality levels
Use the same request shape with other image model families, such as Qwen-Image, Doubao Seedream, or Grok Imagine; start with model and prompt
Pick a current image model ID from the Models page

Safe first request

Start with gpt-image-2
Keep size at 1024x1024
GPT image models return base64-encoded image data in b64_json; decode it to save the image file
Add output_format only when you need a specific encoded image type such as jpeg
Use one prompt and one output image before you add batch generation or style tuning

Run an async image task

Use async: true for long-running image jobs when your client prefers a submit-and-poll flow instead of holding one HTTP connection open. The create request returns data.task_id. Poll Retrieve an image generation task until data.status is success or failure. The async field is a CometAPI extension for this route, not an OpenAI parameter. OpenAI documents stream and partial_images for GPT image models. CometAPI asynchronous task mode returns JSON task metadata and uses polling. Use async task mode with these documented model IDs: gpt-image-2 and doubao-seedream-4-0-250828. For other image models, use synchronous generation or streaming unless async task support is documented for that model. When a request includes both async: true and stream: true, async task mode takes precedence. The create request returns JSON task metadata instead of an SSE stream.

Model-specific request behavior

response_format applies to DALL·E models only; GPT image models return base64 data and ignore it
GPT image models use GPT-only controls such as output_format, quality, background, and output_compression
quality accepts low, medium, high, and auto on GPT image models; gpt-image-2.5-sunburst and gpt-image-2.5-flare also accept xhigh and max
output_compression applies when output_format is webp or jpeg; it has no effect on png
partial_images applies only when stream is true
Follow the OpenAI image generation guide for the latest model-specific options
Other image model families can return the image in url instead of b64_json; read the field that each result item contains

Generate a transparent background

Set background to transparent to generate an isolated subject with no background fill. This is supported on gpt-image-2.5-sunburst and gpt-image-2.5-flare. Transparency needs an output format with an alpha channel. Set output_format to png or webp. JPEG has no alpha channel, so a transparent request with output_format: "jpeg" is rejected. The response returns base64 image data in b64_json with an alpha channel. Decode it to save the file:

import base64
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.cometapi.com/v1",
    api_key=os.environ["COMETAPI_KEY"],
)

result = client.images.generate(
    model="gpt-image-2.5-sunburst",
    prompt="A single red apple, centered, isolated subject.",
    quality="low",
    size="1024x1024",
    background="transparent",
    output_format="png",
)

with open("apple.png", "wb") as f:
    f.write(base64.b64decode(result.data[0].b64_json))

Set background to opaque to force a solid background, or auto to let the model decide. The response echoes the applied value in the top-level background field.

Generated images must comply with provider usage policies. Do not send illegal, violent, pornographic, or copyright-infringing prompts.

Authorizations

Authorization

string

header

required

Bearer token authentication. Use your CometAPI key.

Body

application/json

model

string

default:gpt-image-2

required

The image generation model to use. Choose a current model from the Models page.

prompt

string

required

Text description of the image you want to generate.

Example:

"A paper boat floating on calm water at sunrise."

integer

default:1

Number of images to generate. Keep this at 1 for the broadest compatibility.

quality

string

Quality setting for models that support it. GPT image models accept low, medium, high, and auto. gpt-image-2.5-sunburst and gpt-image-2.5-flare also accept xhigh and max. dall-e-3 accepts standard and hd. See the OpenAI image generation guide for the latest model-specific values.

Example:

"low"

background

enum<string>

Background mode for the generated image. Set transparent to generate an isolated subject with no background fill; this requires output_format set to png or webp, and returns an error with jpeg. Set opaque for a solid background, or auto to let the model decide. Supported on gpt-image-2.5-sunburst and gpt-image-2.5-flare.

Available options:

transparent,

opaque,

auto

output_compression

integer

default:100

Compression level for the output image, from 0 to 100. Applies when output_format is webp or jpeg. Lower values produce smaller files with more compression artifacts.

Required range: 0 <= x <= 100

moderation

enum<string>

default:auto

Content moderation level for GPT image models. low is less restrictive; auto is the default.

Available options:

low,

auto

partial_images

integer

Number of partial images to emit while a streaming response is in progress, from 0 to 3. Each partial image arrives as an image_generation.partial_image event before the final image_generation.completed event. Applies when stream is true.

Required range: 0 <= x <= 3

size

string

Requested output size. Supported values depend on the selected model. See the OpenAI image generation guide for the latest model-specific ranges.

Example:

"1024x1024"

response_format

enum<string>

The response container for dall-e-2 and dall-e-3. This parameter is not supported for GPT image models, which return base64-encoded image data.

Available options:

url,

b64_json

output_format

string

The encoded image type for GPT image model results, such as png, jpeg, or webp. See the OpenAI image generation guide for current GPT image output controls.

Example:

"jpeg"

stream

boolean

default:false

Set this to true to receive server-sent image generation events instead of waiting for the completed JSON response. Streaming responses use text/event-stream and can include final events such as image_generation.completed. When stream and async are both true, async task mode takes precedence and the create request returns JSON instead of a streaming image response.

async

boolean

default:false

CometAPI asynchronous task mode. Set this to true to return immediately with data.task_id, then poll GET /v1/images/generations/{task_id} for the final image data. Documented model IDs for this mode: gpt-image-2 and doubao-seedream-4-0-250828. This is a CometAPI extension, not an OpenAI parameter. When async and stream are both true, async takes precedence and returns JSON task metadata instead of an SSE stream.

Response

Image generation result. Synchronous requests return completed image data. Async requests return a task response with data.task_id.

Completed image response
Async task response

created

integer

required

Unix timestamp for the completed generation.

data

object[]

required

Show child attributes

background

string

Background mode returned by models that expose it.

output_format

string

Encoded image type returned by GPT image models.

quality

string

Quality level returned by models that expose it.

size

string

Output size returned by models that expose it.

usage

object

Token usage details when returned by the selected model.

Show child attributes

Last modified on October 29, 2026

curl https://api.cometapi.com/v1/images/generations \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A paper boat floating on calm water at sunrise.",
    "quality": "low",
    "size": "1024x1024",
    "output_format": "jpeg"
  }'

{
  "created": 1781075000,
  "background": "opaque",
  "output_format": "jpeg",
  "quality": "low",
  "size": "1024x1024",
  "usage": {
    "input_tokens": 13,
    "input_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 13
    },
    "output_tokens": 196,
    "output_tokens_details": {
      "image_tokens": 196,
      "text_tokens": 0
    },
    "total_tokens": 209
  },
  "data": [
    {
      "b64_json": "/9j/4AAQSkZJRgABAQAAAQABAAD..."
    }
  ]
}