Images - MemoryLake AI

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/router/openai/v1/images/generations' \
  -H 'Authorization: Bearer sk_xxxxxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-image-1-mini",
    "prompt": "A small red circle on a white background",
    "quality": "low",
    "size": "1024x1024"
  }'

{
  "created": 1792747467,
  "data": [
    {
      "b64_json": "iVBORw0KGgo…"
    }
  ],
  "usage": {
    "input_tokens": 9,
    "output_tokens": 272,
    "total_tokens": 281
  }
}

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/router/openai/v1/images/generations' \
  -H 'Authorization: Bearer sk_xxxxxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-image-1-mini",
    "prompt": "A small red circle on a white background",
    "quality": "low",
    "size": "1024x1024"
  }'

{
  "created": 1792747467,
  "data": [
    {
      "b64_json": "iVBORw0KGgo…"
    }
  ],
  "usage": {
    "input_tokens": 9,
    "output_tokens": 272,
    "total_tokens": 281
  }
}

POST /openapi/memorylake/router/openai/v1/images/generations

OpenAI Images. Generates images from a text prompt with an image model such as gpt-image-1. Parameters not listed below are passed to the model unchanged.

Headers

string

Your MemoryLake API key, when you call the model with your own provider key. The provider key then goes in the provider’s usual key header. Your provider key is forwarded to the provider and never stored.

string

W3C trace context. When present, the request joins your trace and the same trace id comes back in X-Trace-ID.

Request Body

string

required

Image model name

string

required

Text description of the image

string

Background of the image. One of: transparent, opaque, auto.

integer

Number of images to generate

string

Image file format. One of: png, jpeg, webp.

string

Rendering quality. One of: low, medium, high, auto.

string

Image size, such as 1024x1024

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/router/openai/v1/images/generations' \
  -H 'Authorization: Bearer sk_xxxxxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-image-1-mini",
    "prompt": "A small red circle on a white background",
    "quality": "low",
    "size": "1024x1024"
  }'

Response

integer

Creation time, Unix seconds

array

One entry per image

Show Data object

string

The image, base64-encoded

string

Prompt the model actually used, when it rewrote yours

object

Tokens used

Show Usage object

integer

Tokens in the prompt

integer

Image tokens generated

integer

Sum of input and output tokens

{
  "created": 1792747467,
  "data": [
    {
      "b64_json": "iVBORw0KGgo…"
    }
  ],
  "usage": {
    "input_tokens": 9,
    "output_tokens": 272,
    "total_tokens": 281
  }
}

​Headers

​Request Body

​Response

Headers

Request Body

Response