Skip to main content

​
Welcome to the Crun Models APIs

Explore and integrate cutting-edge AI models for image generation, video creation, and audio processing through unified APIs.

​
Image Models

Comprehensive collection of AI models for image generation, editing, and enhancement.

Google

Google gemini image series (Nano Banana), supporting high-quality image generation and editing with strong realism and semantic understanding.

Seedream

Seedream 5 and 4.x image model series, supporting text-to-image generation with strong detail rendering and style consistency.

Flux

Flux 2, Flux Kontext and Flux Pro image models, supporting text-to-image and image-to-image generation with advanced composition control.

Qwen

Qwen-Image and Qwen-Image-edit possess powerful general capabilities in image generation and editing, and perform exceptionally well in text rendering, especially for Chinese text.

OpenAI

gpt-image-2 models for image generation and editing, featuring strong semantic understanding and high-quality output.

Grok Imagine

High-quality photorealistic images, text-to-image, and greater creativity.

​
Video Models

Advanced AI models for video creation, editing, and transformation from text and images.

Bytedance

Seedance 2.0 and Seedance 2.0 Fast, developed by ByteDance’s Seed team, support text-to-video, image-to-video, and reference-to-video generation with flexible 4-15s duration, audio generation, and strong subject consistency.

Google

Google’s most powerful video generation model series, Veo, features natively synchronized audio, leverages 3 reference images to ensure consistency, and supports a 1080p output resolution.

Wan

Alibaba Wan series of AI video generation models allows creators to produce high-quality, lip-synced 1080p videos from text, audio, images, or reference clips.

Sora2

Sora is OpenAI’s newest frontier in generative media – a state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.

Vidu

Vidu Q series video model boasts powerful image-to-video capabilities, supporting video generation from a single image, start and end frame images, and multiple reference images.

Grok Imagine Video

Grok Imagine powered by xAI’s Aurora engine, supports generating 6-30s videos with sound from images and text, with multiple modes for greater creativity.

​
Language Models

OpenAI-compatible large language models for chat, reasoning, coding, and text generation.

OpenAI-Compatible LLM

Connect CRUN language models through the OpenAI SDK or any client that already supports /chat/completions.

Chat Completions API

Full API reference for the OpenAI-compatible /chat/completions endpoint, including request parameters and streaming.

​
Audio Models

AI-powered audio processing including music generation, speech synthesis, recognition, and effects.

Qwen3 TTS

A unified Text-to-Speech demo featuring three powerful modes: Voice, Clone and Design.

Suno Music API

Supports multiple music models, including the latest Suno V5 model.

​
Getting Started

1

Choose Your Model

Select the AI model that best fits your use case from the categories above.
2

Get API Key

Visit the API Key Management Page to obtain your API credentials.
3

Integrate

Follow the model-specific documentation to integrate the API into your application.
4

Start Creating

Begin generating content using your chosen AI model through simple API calls.

​
Best Practices

All models follow a consistent API structure for ease of integration and invocation.

​
Authentication

All API requests need to include the API key in the request header. 
X-API-KEY: YOUR_API_KEY
Keep your API key secure. Never expose it in client-side code or public repositories.

​
Create Task

All task creation requests follow a unified outer structure. Only the input field varies by model.
Success is only achieved when both the HTTP status code and the business status code are 200.
  curl -X POST "https://api.crun.ai/api/v1/client/job/CreateTask" \
  -H "Content-Type: application/json" \
  -H "X-API-KEY: YOUR_API_KEY" \
  -d '{
    "model": "google/veo3-1-t2v",
    "callback_url": "",
    "input": {
      "...": "model-specific fields"
    }
  }'

​
Response Example

{
  "code": 200,
  "message": "success",
  "data": {
  	"task_id": "xxxx-xxxx"
  }
}

​
Polling Task Status

Polling interval is recommended to be between 15 and 30 seconds. For production environments, we recommend webhook callbacks.
curl -X GET "https://api.crun.ai/api/v1/client/job/TaskInfo?task_id=xxxx-xxxx" \
  -H "Content-Type: application/json" \
  -H "X-API-KEY: YOUR_API_KEY"

​
Response Example

{
  "code": 200,
  "message": "success",
  "data": {
  	"task_id": "3f8e4789-29df-4793-89cc-acb71a1b79d9",
  	"provider": "Google",
  	"model_version": "veo3.1",
  	"status": "running",
  	"param": {
  		"model": "google/veo3-1-t2v",
  		"callback_url": "https://your.domain/api/v1/callback/task",
  		"input": {
  			"...": "model-specific fields"
  		}
  	},
  	"create_at": 1768450365,
  	"result": null,
  	"duration_s": null,
  	"complete_at": null
  }
}
  1. The task status is determined by the status field in the response data object.
  2. When status is success, retrieve the generated media URLs from data.result.media_urls.
  3. When status is failed, check the error code and message in data.result for details.

​
Callback Notifications

Although polling is supported, webhook callbacks are strongly recommended for production systems., When providing callback_url in the task creation request, ensure the following:
  • The endpoint is publicly accessible over HTTPS.
  • It responds quickly (recommended < 3 seconds) to avoid retries.
  • It returns an HTTP 200 status code upon successful receipt.
  • It is idempotent. Callback notifications may be delivered more than once.
Callback payloads use the same structure as the task status query API, allowing a single unified parsing logic.
When the task status changes, we will notify you of the result via a POST request. The payload structure is consistent with the data object returned by the task status query. For production environments, we strongly recommend using callback notifications to retrieve task results.

​
Credits and Pricing

Different models consume different amounts of credits based on their computational requirements:
  • Image Models: Typically 10-50 credits per generation
  • Video Models: Typically 100-500 credits per generation
  • Language Models: Charged per token usage
Visit the pricing page to view detailed pricing for each of our models. Check your remaining credits: 
curl -X POST "https://api.crun.ai/api/v1/client/account/balance" \
  -H "Content-Type: application/json" \
  -H "X-API-KEY: YOUR_API_KEY"

​
Support

Need help choosing the right model or integrating our APIs?