A valid request URL is required to generate request examples{
"id": "<string>",
"created": 123,
"model": "<string>",
"data": [
{
"id": "<string>",
"url": "<string>",
"b64_json": "<string>",
"revised_prompt": "<string>",
"index": 123,
"detections": [
{
"x_min": 123,
"y_min": 123,
"x_max": 123,
"y_max": 123
}
]
}
],
"background": "<string>",
"output_format": "png",
"quality": "<string>",
"size": "256x256",
"usage": {
"input_tokens": 123,
"input_tokens_details": {
"image_tokens": 123,
"text_tokens": 123
},
"total_tokens": 123,
"output_tokens": 123,
"output_tokens_details": {
"image_tokens": 123,
"text_tokens": 123
}
},
"extra_fields": {
"request_type": "<string>",
"provider": "openai",
"model_requested": "<string>",
"model_deployment": "<string>",
"latency": 123,
"chunk_index": 123,
"raw_request": {},
"raw_response": {},
"cache_debug": {
"cache_hit": true,
"cache_id": "<string>",
"hit_type": "<string>",
"requested_provider": "<string>",
"requested_model": "<string>",
"provider_used": "<string>",
"model_used": "<string>",
"input_tokens": 123,
"threshold": 123,
"similarity": 123
}
}
}{
"event_id": "<string>",
"type": "<string>",
"is_bifrost_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "openai",
"model_requested": "<string>",
"request_type": "<string>"
}
}{
"event_id": "<string>",
"type": "<string>",
"is_bifrost_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "openai",
"model_requested": "<string>",
"request_type": "<string>"
}
}Generate an image
Generates images from text prompts using the specified model.
A valid request URL is required to generate request examples{
"id": "<string>",
"created": 123,
"model": "<string>",
"data": [
{
"id": "<string>",
"url": "<string>",
"b64_json": "<string>",
"revised_prompt": "<string>",
"index": 123,
"detections": [
{
"x_min": 123,
"y_min": 123,
"x_max": 123,
"y_max": 123
}
]
}
],
"background": "<string>",
"output_format": "png",
"quality": "<string>",
"size": "256x256",
"usage": {
"input_tokens": 123,
"input_tokens_details": {
"image_tokens": 123,
"text_tokens": 123
},
"total_tokens": 123,
"output_tokens": 123,
"output_tokens_details": {
"image_tokens": 123,
"text_tokens": 123
}
},
"extra_fields": {
"request_type": "<string>",
"provider": "openai",
"model_requested": "<string>",
"model_deployment": "<string>",
"latency": 123,
"chunk_index": 123,
"raw_request": {},
"raw_response": {},
"cache_debug": {
"cache_hit": true,
"cache_id": "<string>",
"hit_type": "<string>",
"requested_provider": "<string>",
"requested_model": "<string>",
"provider_used": "<string>",
"model_used": "<string>",
"input_tokens": 123,
"threshold": 123,
"similarity": 123
}
}
}{
"event_id": "<string>",
"type": "<string>",
"is_bifrost_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "openai",
"model_requested": "<string>",
"request_type": "<string>"
}
}{
"event_id": "<string>",
"type": "<string>",
"is_bifrost_error": true,
"status_code": 123,
"error": {
"type": "<string>",
"code": "<string>",
"message": "<string>",
"param": "<string>",
"event_id": "<string>"
},
"extra_fields": {
"provider": "openai",
"model_requested": "<string>",
"request_type": "<string>"
}
}Authorizations
Bearer token authentication. Use your provider API key or Bifrost authentication token.
Virtual keys (prefixed with sk-bf-) can also be passed here.
Body
Model identifier in format provider/model
Text prompt to generate image
Number of images to generate
1 <= x <= 10Size of the generated image
256x256, 512x512, 1024x1024, 1792x1024, 1024x1792, 1536x1024, 1024x1536, auto Quality of the generated image
auto, high, medium, low, hd, standard Style of the generated image
natural, vivid Format of the response. data_uri is supported by providers that return an inline
data URI (e.g. Runware).
url, b64_json, data_uri Input images for image-to-image generation, as public URLs, provider-side asset IDs, or base64 data URIs. Providers that accept only a single input use the first entry.
Aspect ratio of the generated image (e.g. 16:9), for providers that accept one in place of size
Operation selector for providers that expose more than one generation task
(e.g. vectorize for text-to-SVG on Runware). Omit for standard generation.
Background type for the image
transparent, opaque, auto Content moderation level
low, auto Number of partial images to generate
0 <= x <= 3Compression level (0-100%)
0 <= x <= 100Output image format. svg applies to vectorize operations
png, webp, jpeg, tiff, svg User identifier for tracking
Seed for reproducible image generation
Negative prompt to guide what to avoid in generation
Number of inference steps for generation
Whether to stream the response. When true, images are sent as SSE.
When streaming, providers may return base64 chunks (b64_json) and/or URLs (url) depending on provider and configuration.
Fallback models to try if primary model fails
Show child attributes
Show child attributes
Response
Successful response. Returns JSON for non-streaming requests, or Server-Sent Events (SSE) stream when stream=true.
When streaming, events are sent with the following event types:
image_generation.partial_image: Intermediate image chunks with base64-encoded image dataimage_generation.completed: Final event for each image with usage informationerror: Error events with error details
Unique identifier for the generation request
Unix timestamp when the image was created
Model used for generation
Array of generated images
Show child attributes
Show child attributes
Background type for the image
Output image format
png, webp, jpeg Quality of the generated image
Size of the generated image
256x256, 512x512, 1024x1024, 1792x1024, 1024x1792, 1536x1024, 1024x1536, auto Show child attributes
Show child attributes
Additional fields included in responses
Show child attributes
Show child attributes
Was this page helpful?