General API

OpenAI-compatible Gemini image generation and reference-image editing with URL output.

The compatible endpoint follows the OpenAI image format and normally returns an image URL.

Endpoint Information

Item	Value
Endpoint	`POST https://api.tokenhub.belivestudios.com/v1/images/generations`
Authentication	Header `Authorization: Bearer sk-your-belive-studios-key`
Content-Type	`application/json`

Generate

curl https://api.tokenhub.belivestudios.com/v1/images/generations \
  -H "Authorization: Bearer sk-your-belive-studios-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "prompt": "A cat running through a neon street after rain, cinematic",
    "size": "1k",
    "aspect_ratio": "1:1",
    "response_format": "url"
  }'

Reference-Image Editing

Some models support reference images. Put the reference image URL in the request body's image array; use prompt only for the text editing instruction:

curl https://api.tokenhub.belivestudios.com/v1/images/generations \
  -H "Authorization: Bearer sk-your-belive-studios-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "prompt": "Keep the person unchanged and replace the background with a beach sunset",
    "size": "1k",
    "aspect_ratio": "16:9",
    "response_format": "url",
    "image": [
      "https://example.com/reference.jpg"
    ]
  }'

Response

Image generation and reference-image editing use the same response structure. After a successful request, the generated image URL is in data[0].url.

{
  "created": 1787888579,
  "data": [
    {
      "b64_json": "",
      "revised_prompt": "",
      "url": "https://cdn.aiznt.com/relay-temp-images/20260828/b13c70b8-5e24-4936-a54f-d158aadf980a.jpg"
    }
  ]
}

Field	Type	Description
`created`	integer	Unix timestamp, in seconds, when the response was created
`data`	array	List of generated image results
`data[].url`	string	Temporary URL for the generated image
`data[].b64_json`	string	Base64 image data; normally an empty string in URL response mode
`data[].revised_prompt`	string	Server-revised prompt; normally an empty string when none is provided

Temporary image URL

Download and store the image promptly after receiving the response. Do not use the temporary URL as permanent storage.

Python

import requests

response = requests.post(
    "https://api.tokenhub.belivestudios.com/v1/images/generations",
    headers={"Authorization": "Bearer sk-your-belive-studios-key"},
    json={
        "model": "gemini-3.1-flash-image",
        "prompt": "A cat running through a neon street after rain, cinematic",
        "size": "1k",
        "aspect_ratio": "1:1",
        "response_format": "url",
    },
    timeout=300,
)
response.raise_for_status()
print(response.json()["data"][0]["url"])

Parameters

Parameter	Description
`model`	Gemini image model ID
`prompt`	Generation or editing instruction
`image`	Reference image array, when supported by the selected model
`size`	Commonly `1k` or `2k`, subject to model support
`aspect_ratio`	Ratio such as `1:1` or `16:9`
`response_format`	Usually `url`

Use the current console endpoint definition for the complete fields and model capabilities.