Text to Image

curl --request POST \
  --url https://api.maxapi.io/api/v1/task/submit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "seedream-4.5",
  "callBackUrl": "https://example.com/webhook",
  "input": {
    "prompt": "Cyberpunk Tokyo street",
    "ratio": "16:9",
    "resolution": "2k"
  }
}'

{
  "code": 0,
  "msg": "ok",
  "data": {
    "taskId": "9db7d1ed-d1e5-4d11-9f3a-61f653b905ad"
  }
}

POST

api

task

submit

curl --request POST \
  --url https://api.maxapi.io/api/v1/task/submit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "seedream-4.5",
  "callBackUrl": "https://example.com/webhook",
  "input": {
    "prompt": "Cyberpunk Tokyo street",
    "ratio": "16:9",
    "resolution": "2k"
  }
}'

{
  "code": 0,
  "msg": "ok",
  "data": {
    "taskId": "9db7d1ed-d1e5-4d11-9f3a-61f653b905ad"
  }
}

Use Seedream image models to generate images from a prompt. 3 model versions are supported.

Available Models

seedream-5-lite · seedream-4.5 · seedream-4

string

required

Model name, e.g. seedream-4.5, seedream-5-lite.

string

Webhook callback URL.

object

required

Hide properties

string

required

Prompt describing the image you want to generate.

string

Image aspect ratio. Options: 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9.

string

Resolution. Options: 1k, 2k, 4k.

integer

Number of images to generate. Default 1. Billing scales linearly with n.

seedream-5-lite: 1–4
seedream-4 / seedream-4.5: 1–15

curl --request POST \
  --url https://api.maxapi.io/api/v1/task/submit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "seedream-4.5",
  "callBackUrl": "https://example.com/webhook",
  "input": {
    "prompt": "Cyberpunk Tokyo street",
    "ratio": "16:9",
    "resolution": "2k"
  }
}'

{
  "code": 0,
  "msg": "ok",
  "data": {
    "taskId": "9db7d1ed-d1e5-4d11-9f3a-61f653b905ad"
  }
}

Query Result

Retrieve the generation result via the Query Task endpoint or Webhook:

{
  "code": 0,
  "msg": "ok",
  "data": {
    "taskId": "9db7d1ed-d1e5-4d11-9f3a-61f653b905ad",
    "status": "SUCCESS",
    "input": {
      "model": "seedream-4.5",
      "prompt": "Cyberpunk Tokyo street",
      "ratio": "16:9",
      "resolution": "2k"
    },
    "result": {
      "type": "image",
      "urls": [
        "https://example.com/output/image1.png",
        "https://example.com/output/image2.png",
        "https://example.com/output/image3.png",
        "https://example.com/output/image4.png"
      ]
    },
    "created_at": "2026-02-10T21:54:46.686768Z",
    "updated_at": "2026-02-10T21:55:04.039815Z"
  }
}

Image generation typically returns multiple images. result is only populated when status is SUCCESS.

Overview

Task API

Veo 3 Video

Nano Banana Image

Seedream Image

Grok Imagine (xAI)

GPT Image 2 (OpenAI)

Available Models

Query Result

​Available Models

​Query Result

Available Models

Query Result