Create response - Modular Cloud

POST

/

v1

/

responses

import base64
from openai import OpenAI

client = OpenAI(
    base_url="https://api.modular.com/v1",
    api_key="<your-api-key>",  # Load your key
)

response = client.responses.create(
    model="black-forest-labs/FLUX.2-klein-4B",
    input="A serene mountain landscape at sunset",
    extra_body={
        "provider_options": {
            "image": {"height": 1024, "width": 1024, "steps": 4}
        }
    },
)

image_data = response.output[0].content[0].image_data
with open("output.png", "wb") as f:
    f.write(base64.b64decode(image_data))

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1786985535,
  "status": "completed",
  "model": "black-forest-labs/FLUX.2-klein-4B",
  "output": [
    {
      "id": "msg_abc123_0",
      "role": "assistant",
      "content": [
        {
          "type": "output_image",
          "image_data": "/9j/4AAQSkZJRgABAQAA...",
          "format": "jpeg"
        }
      ],
      "status": "completed"
    }
  ],
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0,
    "total_tokens": 0,
    "image_generation_details": {
      "width": 1024,
      "height": 1024,
      "megapixels": 1.048576,
      "steps": 4,
      "image_count": 1
    }
  }
}

Send a text prompt or image to generate a new image or video. See the Supported models page to find which models support these different modalities.

Authorizations

Authorization

string

header

required

Modular Cloud API key. Obtain from the API keys page.

Body

application/json

model

string

required

Model identifier. See the supported models page.

Example:

"black-forest-labs/FLUX.2-klein-4B"

input

required

Model input. Pass a plain string for text-to-image/video, or a structured content array for image-to-image/video.

seed

integer

Random seed for reproducible outputs.

provider_options

object

Show child attributes

Response

200 - application/json

Response object containing generated content.

id

string

required

Unique identifier for the response.

object

enum<string>

required

The object type. Always response.

Available options:

response

created_at

integer

required

Unix timestamp (in seconds) of when the response was created.

status

enum<string>

required

The status of the response.

Available options:

completed,

failed

model

string

required

The model used to generate the response.

output

object[]

required

The messages generated by the model.

Show child attributes

usage

object

required

Usage statistics for the response.

Show child attributes

⌘I

import base64
from openai import OpenAI

client = OpenAI(
    base_url="https://api.modular.com/v1",
    api_key="<your-api-key>",  # Load your key
)

response = client.responses.create(
    model="black-forest-labs/FLUX.2-klein-4B",
    input="A serene mountain landscape at sunset",
    extra_body={
        "provider_options": {
            "image": {"height": 1024, "width": 1024, "steps": 4}
        }
    },
)

image_data = response.output[0].content[0].image_data
with open("output.png", "wb") as f:
    f.write(base64.b64decode(image_data))

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1786985535,
  "status": "completed",
  "model": "black-forest-labs/FLUX.2-klein-4B",
  "output": [
    {
      "id": "msg_abc123_0",
      "role": "assistant",
      "content": [
        {
          "type": "output_image",
          "image_data": "/9j/4AAQSkZJRgABAQAA...",
          "format": "jpeg"
        }
      ],
      "status": "completed"
    }
  ],
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0,
    "total_tokens": 0,
    "image_generation_details": {
      "width": 1024,
      "height": 1024,
      "megapixels": 1.048576,
      "steps": 4,
      "image_count": 1
    }
  }
}