API docsAPI reference

OpenAI-compatible images

POST /images/generations accepts the OpenAI images API, so the OpenAI SDKs, LobeChat, Cherry Studio, Dify and n8n can use every image model here. size maps to the closest aspect_ratio, n to num_images, and any model parameter can be passed as an extra field. It waits up to ~110s; a slower task returns 504 with its id to poll.

POST/api/v1/images/generationsBearer API key

Request

cURL

curl 'https://01router.com/api/v1/images/generations' \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nano-banana-pro",
  "prompt": "A minimalist poster of a paper crane",
  "size": "1024x1024"
}'

Input parameters

JSON body

model stringRequired: Model slug from the catalog. Project keys may use a project-specific model slug.
prompt stringRequired: Text describing the requested image. Required and non-empty.
provider stringOptional: Optional provider slug. Omit for automatic routing; project settings may pin the provider.
project stringOptional: Optional project ID. Use its published model catalog and routing configuration.
size stringOptional: Width x height, such as 1024x1024, or auto. Maps to the nearest supported aspect ratio when needed.
n integerOptional: Positive integer, default 1. Multiple images require the model to support num_images.
Default:1
Minimum:1
response_format stringOptional: url (default) or b64_json. If base64 conversion fails or exceeds the size limit, that item falls back to a URL.
Default:"url"
Allowed values:"url""b64_json"

Response example

200 · application/json

{
  "created": 1792915200,
  "data": [
    {
      "url": "https://example.com/result.png"
    }
  ],
  "id": "gen_example",
  "model": "nano-banana-pro",
  "credits": 10
}

Responses are illustrative. IDs, usage, prices and results depend on the actual request.

Response fields

created integer: Unix timestamp in seconds.
data array: Each item has url or b64_json depending on response_format and conversion availability.
id string: Generation ID returned by the create request.
model string: Model slug from the catalog. Project keys may use a project-specific model slug.
credits number: Credits charged for this generation; zero after a refund.

Usage notes

Poll at intervals of at least 3 seconds. A 504 from the synchronous image endpoint means the task may still be running: poll its error.id instead of submitting it again.
For /generations and /quote, put these parameters inside input. For /images/generations, put them at the top level. Chat parameters go at the top level of /chat/completions.

Use with AI

Give your coding assistant the documentation index or the full API reference, including live model parameters.

llms.txt llms-full.txt This page as Markdown