liangxin
    • Market
    • Image Models
      • Seedream
        • Seedream4.5 - Text to Image
        • Seedream4.5 - Edit Image
        • Seedream5.0 Lite - Text to Image
        • Seedream5.0 Lite - Edit Image
      • Z-image
        • Z-Image
      • Google
        • Google - Gemini 2.5 Flash Image Preview
        • Google - Nano Banana Pro
        • Google - Nano Banana Pro Flash
        • Google - imagen4-fast
        • Google - imagen4-ultra
      • Flux-2
        • Flux-2 - Pro Text to Image
    • Video Models
      • Kling
        • Kling 3 Pro - Generate Video
    • Get Task Details
      GET

    Market

    Market#

    Explore and integrate cutting-edge AI models for image generation through unified APIs.

    Welcome To The Market#

    LiangXin Market provides a unified task API for AI image models. Instead of learning every upstream provider's authentication, task format, polling style, and webhook behavior, you call one LiangXin API and select the target model with the model field.

    Image Models#

    Use the Image Models section for model-specific request parameters and examples.
    Z-image: creative text-to-image generation.
    Seedream: Seedream 4.5 and Seedream 5.0 Lite text-to-image models.
    Google: Gemini 2.5 Flash Image Preview, Nano Banana Pro, Nano Banana Pro Flash, Imagen 4 Fast, and Imagen 4 Ultra.
    Flux-2: Flux 2 Pro text-to-image and image-guided generation.

    Getting Started#

    1.
    Choose your model from Image Models.
    2.
    Create an API key in the LiangXin console.
    3.
    Submit a task with POST /api/v1/jobs/createTask.
    4.
    Store the returned taskId.
    5.
    Poll GET /api/v1/jobs/recordInfo or receive a callBackUrl webhook.

    Authentication#

    All Market APIs use the same authentication method:
    Keep your API key confidential. Never expose it in browser code, mobile app bundles, public repositories, or customer-visible logs.

    Unified API Structure#

    Create Task#

    Example:
    {
      "model": "z-image",
      "callBackUrl": "https://your-domain.com/api/liangxin/callback",
      "input": {
        "prompt": "A cinematic product photo of a tea bottle on a stone table",
        "aspect_ratio": "1:1"
      }
    }

    Query Task Status#

    Callback Notifications#

    If callBackUrl is provided, LiangXin sends the final task payload to your server after the task reaches success or fail.
    Your integration should still support polling because webhook delivery can fail due to network restrictions, DNS issues, firewall rules, or non-2xx responses from your server.

    Result Format#

    When the task succeeds, read generated files from data.resultJson.
    {
      "code": 200,
      "msg": "success",
      "data": {
        "taskId": "lx_task_01JZ2Q7YH9K6C2KQ5G7P8F2N6M",
        "model": "z-image",
        "state": "success",
        "resultJson": "{\"resultUrls\":[\"https://cdn.example.com/result.png\"]}"
      }
    }

    Credits And Pricing#

    Different models consume different amounts of credits based on upstream cost and generation complexity.
    Check model pricing in the LiangXin console before production use.

    Support#

    If you need help choosing a model or debugging integration behavior, contact LiangXin support and include:
    Request model name.
    Request body without your API key.
    Returned taskId.
    Error response or webhook payload.
    Modified at 2026-05-01 05:51:39
    Next
    Seedream4.5 - Text to Image
    Built with