Docs
  1. Tutorials
Docs
  • Introduction
  • Quick Start Guide
  • Make a request
  • YEScale System API Tutorial
  • Chat Models
    • ChatGpt
      • ChatGPT (Audio)
        • Create transcription by gpt-4o-mini-transcribe & gpt-4o-transcribe
        • Create a voice with gpt-4o-mini-tts
        • Create a voice
        • Create a transcript
        • Create translation
      • ChatGPT (Chat)
        • Chat completion object
        • Create chat completion (streaming)
        • Create chat completion (non-streaming)
        • Create chat image recognition (streaming)
        • Create chat image recognition (streaming) base64
        • Create chat image recognition (non-streaming)
        • Function calling
        • N choices
        • Create chat function call (only non-streaming)
        • Create structured output
      • ChatGPT (Completions)
        • Completion object
        • Creation completed
      • ChatGPT(Embeddings)
        • Embedded Object
        • Create embed
    • Anthropic Claude
      • Offical Format
        • Messages (official Anthropic format)
        • Messages(Image Recognition)
        • Messages(function call)
        • Messages(Web search)
      • Create chat completion (streaming)
      • Create chat completion (non-streaming)
      • Create chat image recognition (streaming)
      • Create chat image recognition (non-streaming)
    • Gemini
      • Gemini Image creation interface (gemini-2.0-flash-exp-image-generation)
      • Chat interface
      • Image recognition interface
      • Function calling - Google Search
      • Function calling - codeExecution
  • Image Models
    • GPT-IMAGE-1
      • Generate Image by gpt-image-1
      • Edit Image by gpt-image-1
    • MJ
      • Submit Imagine task (mj_imagine)
      • Submit Blend task (mj_blend)
      • Submit Describe task (mj_describe)
      • Submit Change task (mj_variation, mj_upscale,mj_reroll)
      • Query task status based on task ID
    • Ideogram
      • Generate with Ideogram 3.0
      • Edit with Ideogram 3.0
      • Remix with Ideogram 3.0
      • Ideogram Upscale
    • Kling Image
      • Submit Image Generation
      • Get Image by Task ID
      • Submit Kolors Virtual Try On
      • Get Kolors Virtual Try On by Task ID
    • Flux
      • Flux on Replicate
        • Submit Image by flux-kontext-pro
        • Submit Image by flux-kontext-max
        • Submit Image by flux-pro
        • Submit Image by flux-pro-1.1-ultra
        • Get Image by ID
    • Recraft API
      • Recraft Image
      • Generate Image
      • Generate Vector Image
      • Remove Background
      • Clarity Upscale
      • Generative Upscale
    • Models use Dall-e Format
      • Google Imagen
      • Bytedance - seedream-3.0
      • Recraftv3 use Dall-e endpoint
      • Flux use Dall-e endpoint
    • Google Imagen
      • Google/imagen-4 on Replicate
      • Get Imagen 4 Task
    • DALL·E 3
      POST
  • Video Models
    • Kling Video
      • Create Video by Text
      • Get Video by Task ID(text2video)
      • Create Video by Image
      • Get Video by Task ID(image2video)
    • Runway ML Video
      • Create Video by Runway
      • Get Video by Task ID
    • Luma Video
      • Create Video by Luma
      • Get Video by Task ID
    • Pika Video
      • Create Video by Pika
      • Get Video by Task ID
    • Google Veo
      • Submit Video Request
      • Submit Video Request with Frames
      • Get Video by ID
    • Minimax - Hailuo
      • Submit Video Request
      • Get Video
    • Seedance
      • Submit Video Request
      • Get Video by Task ID
    • Mj Video
      • Submit Mj Video Request
      • Get Mj Video by task id
  • FAL-AI Models
    • Images Models
      • Ideogram/v3/remix
      • Flux-pro/kontext/max
      • Fal-recraft-v3-text-to-image
      • Fal-recraft-v3-image-to-image
      • Fal-bytedance-seededit-v3-edit-image
    • Audio Models
      • Minimax/speech-02-hd
      • Minimax/speech-02-turbo
      • Elevenlabs/tts/turbo-v2.5
      • Elevenlabs/tts/multilingual-v2
    • Video Models
      • Topaz/upscale/video
      • Luma-dream-machine/ray-2-flash/reframe
      • Luma-dream-machine/ray-2/reframe
    • Get FAL-AI tasks
  • Music Model - Suno
    • Illustrate
    • Parameter
    • Task submission
      • Generate songs (inspiration, customization, continuation)
      • Generate lyrics
    • Query interface
      • Query a single task
  • Python Samples
    • python openai official library (using AutoGPT, langchain, etc.)
    • Python uses speech to text
    • Python uses text to speech
    • Python uses Embeddings
    • python calls DALL·E
    • python simple call openai function-calling demo
    • python langchain
    • python llama_index
    • Python uses gpt-4o to identify pictures-local pictures
    • python library streaming output
    • Python uses gpt-4o to identify images
  • Plug-in/software usage tutorials
    • Setting HTTP for Make.com with Yescale
    • Sample Code for gpt-4o-audio/gpt-4o-mini-audio
  • Help Center
    • HTTP status codes
  • Tutorials
    • GPT-Image-1 API: A Step-by-Step Guide With Examples
    • Claude Code via YEScale API
    • Task Sync Endpoint Usage Guide
  1. Tutorials

Task Sync Endpoint Usage Guide

Endpoint#

GET /task/{task_id}
Authentication: Required (API Key in header: Authorization: Bearer <API_KEY>)

Description#

This endpoint allows you to fetch the latest, unified result of any task in the system by its task_id. It supports all platforms (Kling, Suno, Luma, Pika, Replicate, RunwayML, Seedance, Hailuo, Veo3, FalAI, MJVideo, Midjourney, etc.).
The response is normalized, making it easy for clients to parse and display results regardless of the underlying platform.

Request Example#

GET /task/777935781150867525
Authorization: Bearer sk-xxxxxxx

Response Structure#

{
  "task_id": "string",           // The unique ID of the task
  "status": "string",            // Task status: SUCCESS | FAILURE | ...
  "progress": "string",          // Progress percentage (e.g. "100%")
  "err_reason": "string",        // Error reason if status is FAILURE (may be empty)
  "submit_time": number,          // Unix timestamp when the task was submitted
  "finish_time": number,          // Unix timestamp when the task finished
  "message": "string",           // Human-readable message (includes platform, action, etc.)
  "task_result": {                // Main result data, see below for details
    "videos": [                   // (optional) List of video results
      {
        "url": "string",        // Direct link to the video file
        "duration": "string|number", // (optional) Duration in seconds
        "content_type": "string" // (optional) MIME type, e.g. "video/mp4"
      }
    ],
    "images": [                   // (optional) List of image results
      {
        "url": "string",        // Direct link to the image file
        "content_type": "string" // (optional) MIME type, e.g. "image/png"
      }
    ],
    "audio": [                    // (optional) List of audio results
      {
        "url": "string",        // Direct link to the audio file
        "duration": "string|number", // (optional) Duration in seconds
        "content_type": "string" // (optional) MIME type, e.g. "audio/mpeg"
      }
    ],
    "text": "string"             // (optional) Text result, e.g. lyrics or error message
  }
}

Notes#

If the task is not found in the main task table, the system will automatically look up in the Midjourney table.
The response is always normalized for easy client-side handling.
If status is FAILURE, the field err_reason will always be present (may be empty).
The task_result object will only contain relevant fields for the platform and task type.

Example Error Response#

{
  "error": "Task not found"
}
Modified at 2025-07-27 06:48:50
Previous
Claude Code via YEScale API
Built with