Generate Image

Creates an image from a text prompt. The endpoint definition follows the OpenAI Create image API.

Endpoint

Model Selection

The examples below use per-use models. To use an official model, replace the request's model value.

Examples

curl https://api.tokenhub.belivestudios.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-belive-studios-key" \
  -d '{
    "model": "gpt-image-2.5-sunburst",
    "prompt": "A cute baby sea otter",
    "n": 1,
    "size": "1024x1024"
  }'

{
  "created": 1713833628,
  "data": [
    {
      "b64_json": "..."
    }
  ],
  "usage": {
    "total_tokens": 100,
    "input_tokens": 50,
    "output_tokens": 50,
    "input_tokens_details": {
      "text_tokens": 10,
      "image_tokens": 40
    }
  }
}

Request Parameters

Core Parameters

prompt

Type: string, required

A text description of the desired image. The maximum length is 32,000 characters for GPT Image models, 1,000 for dall-e-2, and 4,000 for dall-e-3.

background

Type: "transparent" | "opaque" | "auto" | null, optional

Sets the background of the generated image. Supported only by GPT Image models. auto is the default and lets the model choose the best background.

gpt-image-2.5-sunburst, gpt-image-2.5-flare, and their 2026-09-08 snapshots support opaque and transparent backgrounds. Transparent backgrounds are also available for other supported GPT Image models. Support for gpt-image-2 and gpt-image-2-2026-04-21 is in preview. When using transparent, set output_format to png or webp.

model

Type: string | ImageModel | null, optional

The image-generation model. Platform model names are grouped as follows:

• Per-use models: gpt-image-2, gpt-image-2.5-sunburst, and gpt-image-2.5-flare
• Official models: gpt-image-2-2026-04-21, gpt-image-2.5-sunburst-2026-09-08, and gpt-image-2.5-flare-2026-09-08

moderation

Type: "low" | "auto" | null, optional

Controls content moderation for GPT Image models. low applies less restrictive filtering; auto is the default.

n

Type: number | null, optional

The number of images to generate, from 1 to 10. dall-e-3 supports only n=1.

Output Controls

output_compression

Type: number | null, optional

Compression level from 0 to 100 percent, defaulting to 100. Supported only by GPT Image models when output_format is webp or jpeg.

output_format

Type: "png" | "jpeg" | "webp" | null, optional

The generated image format. Supported only by GPT Image models.

partial_images

Type: number | null, optional

The number of partial images to generate in a streaming response, from 0 to 3. When set to 0, the response sends only the final image in a single streaming event. The final image may arrive before all requested partial images if it is generated sooner.

quality

Type: "standard" | "hd" | "low" | "medium" | "high" | "xhigh" | "max" | "auto" | null, optional

• auto: automatically selects the best quality and is the default
• high, medium, and low: supported by GPT Image models
• xhigh and max: supported by gpt-image-2.5-sunburst, gpt-image-2.5-flare, and their 2026-09-08 snapshots
• hd and standard: supported by dall-e-3
• standard: the only option supported by dall-e-2

Streaming and Compatibility

response_format

Type: "url" | "b64_json" | null, optional

Sets the response format for dall-e-2 and dall-e-3. URLs are valid for 60 minutes. GPT Image models do not support this parameter and always return base64-encoded images.

size

Type: string | "auto" | null, optional

• GPT Image models support 1024x1024, 1536x1024, and 1024x1536; models with automatic sizing also support auto
• gpt-image-2, gpt-image-2-2026-04-21, both GPT Image 2.5 models, and their 2026-09-08 snapshots support arbitrary WIDTHxHEIGHT resolutions, such as 1536x864
• dall-e-2 supports 256x256, 512x512, and 1024x1024
• dall-e-3 supports 1024x1024, 1792x1024, and 1024x1792

For the models listed above that support arbitrary resolutions, both dimensions must be divisible by 16, the aspect ratio must be between 1:3 and 3:1, and the request must meet the model's current pixel and edge limits. Resolutions above 2560x1440 are experimental; the maximum is 3840x2160.

stream

Type: boolean | null, optional

Generates the image in streaming mode. Defaults to false and is supported only by GPT Image models.

style

Type: "vivid" | "natural" | null, optional

Sets the generated image style. Supported only by dall-e-3. vivid favors hyper-real, dramatic images; natural produces a more natural appearance.

user

Type: string, optional

A unique identifier for the end user that can help monitor and detect abuse.

Response

The endpoint returns an ImagesResponse object.

data Fields

usage Fields