Funcreator

API Documentation

AI generation APIs (video & LLM chat) authenticated with APIKey

APIKey Authentication

All generation endpoints (video generation and LLM chat) use APIKey for authentication; no prior login is required.

Include it in the request header:

Authorization: Bearer <apiKey>

APIKeys are created and managed on the API Keys page (login required first).

Basic Information

Server http://localhost:8899

Base Path

/Api/v1/VideoGen /Api/v1/LLM

Rate Limit APIKey requests are limited to 3 per second; multiple consecutive invalid APIKeys will blacklist the IP

Response Format Video endpoints return {"Success": true, "Message": "...", "Data": {...}}; LLM endpoints use the OpenAI-compatible format (see below)

HTTP Status Codes

Status Code	Meaning
200	Request successful
400	Invalid request parameters
401	Invalid APIKey / unauthenticated
402	Insufficient balance
403	Forbidden - invalid model or parameters
429	Too many requests (rate limited)
500	Internal server error

Endpoint List

POST /Api/v1/VideoGen/gensd Generate video (SD multimodal)

Pass multimodal inputs (text/image/video/audio) through a unified content array, and the SDK automatically distributes them to the corresponding fields. Suitable for scenarios requiring multiple reference materials at once.

Request Body (JSON)

{
  "model": "SD",
  "duration": 5,
  "resolution": "720p",
  "ratio": "16:9",
  "content": [
    { "type": "text", "text": "A cat walking on the street" },
    { "type": "image_url", "role": "reference_image", "image_url": { "url": "https://..." } },
    { "type": "video_url", "role": "reference_video", "video_url": { "url": "https://..." } },
    { "type": "audio_url", "role": "reference_audio", "audio_url": { "url": "https://..." } },
    { "type": "image_url", "role": "first_frame", "image_url": { "url": "https://..." } }
  ]
}

Parameter Description

Field	Type	Required	Description
model	string	Yes	Model name: `SD`
content	array	Yes	Multimodal content list (text / image_url / video_url / audio_url)
duration	int	Yes	Video duration (seconds)
resolution	string	Yes	`480p` / `720p` / `1080p`
ratio	string	No	Aspect ratio, e.g. `16:9`

content Sub-item Field Description

Field	Type	Description
type	string	`text` / `image_url` / `video_url` / `audio_url`
text	string	Text content (used when `type=text`)
image_url	object	Image URL object `{"url": "..."}` (used when `type=image_url`)
video_url	object	Video URL object `{"url": "..."}` (used when `type=video_url`)
role	string	`first_frame` / `reference_image` / `reference_video` / `reference_audio`

role Constraint Description

role	Corresponding Field	Quantity Limit
text	text	1
reference_image	image_url	Up to 9 (Reference Image)
reference_video	video_url	Up to 1 (Reference Video)
reference_audio	audio_url	Up to 1 (Reference Audio)
first_frame	image_url	Up to 1 (First Frame Image)

Successful Response

{
  "id": "xxx"
}

Error Response (OpenAI format)

{
  "error": {
    "code": "invalid_parameters",
    "message": "Incorrect parameters"
  }
}

POST /Api/v1/VideoGen/gen Generate video

Automatically routes to the SD / HH / YK / WAN service based on ModelName.

Request Body (JSON)

{
  "modelName": "SD",
  "prompt": "A cat walking on the street",
  "duration": 5,
  "resolution": "720p",
  "imageUrl": "https://...",
  "referenceVideoUrl": "https://...",
  "referenceAudioUrl": "https://...",
  "aspectRatio": "16:9",
  "images": ["https://...", "https://..."]
}

Parameter Description

Field	Type	Required	Description
modelName	string	Yes	Model name: `SD` / `HH` / `YK` / `WAN` (or `TEST`)
prompt	string	Yes	Prompt text
duration	int	Yes	Video duration (seconds)
resolution	string	Yes	`480p` / `720p` / `1080p`
imageUrl	string	No	First frame / reference image URL
referenceVideoUrl	string	No	Reference video URL
referenceAudioUrl	string	No	Reference audio URL
aspectRatio	string	No	Aspect ratio, e.g. `16:9`
images	string[]	No	Reference image list (media URLs)

Successful Response

{
  "id": "xxx"
}

Error Response (OpenAI format)

{
  "error": {
    "code": "invalid_api_key",
    "message": "API Key does not exist or has insufficient permissions"
  }
}

HTTP Status Code Description

Status Code	error.code	Description
401	invalid_api_key	API Key invalid or insufficient permissions
402	insufficient_balance	Insufficient account balance
403	invalid_model	Incorrect model
403	invalid_parameters	Incorrect parameters
500	internal_error	Internal server error

POST /Api/v1/VideoGen/status Query video task status

Request Body (JSON)

{
  "id": "xxx"
}

Parameter Description

Field	Type	Required	Description
id	string	Yes	The ID returned by the video generation task

Successful Response (Completed)

{
  "id": "xxx",
  "model": "SD",
  "status": "succeeded",
  "created_at": "2025-01-01T00:00:00Z",
  "expire_at": "2025-01-02T00:00:00Z",
  "content": [
    {
      "type": "video",
      "video_url": "https://...",
      "duration": 5,
      "resolution": "720p"
    }
  ],
  "usage": {
    "credits": 10.0,
    "token": 0
  }
}

Successful Response (Processing)

{
  "taskid": "xxx",
  "model": "SD",
  "status": "pending",
  "created_at": "2025-01-01T00:00:00Z"
}

Successful Response (Failed)

{
  "id": "xxx",
  "model": "SD",
  "status": "failed",
  "created_at": "2025-01-01T00:00:00Z",
  "error": {
    "message": "Failure reason"
  },
  "usage": {
    "credits": 0,
    "token": 0
  }
}

Status Description

status Value	Description
pending	Processing
succeeded	Completed
failed	Failed

POST /Api/v1/VideoGen/audit Submit asset for review

Submit the asset for review. The full URL of the asset must be provided.

Request Body (JSON)

{
  "url": "https://...",
  "name": "Asset name",
  "type": "Image"
}

Parameter Description

Field	Type	Required	Description
url	string	Yes	Asset URL to be reviewed
name	string	Yes	Asset name
type	string	No	`Image` / `Video` / `Audio`

Successful Response

{
  "Success": true,
  "Message": "Review submitted successfully",
  "Data": {
    "TaskId": "xxx",
    "AssetId": "yyy"
  }
}

POST /Api/v1/VideoGen/auditstatus Query asset review status

Request Body (JSON)

{
  "assetId": "yyy"
}

Parameter Description

Field	Type	Required	Description
assetId	string	Yes	The AssetId returned by the review task

Successful Response

{
  "Success": true,
  "Message": "Review status query successful",
  "Data": {
    "Status": 1,
    "ServerStatus": "approved"
  }
}

Status Description

status Value	Description
1	Approved
2	Reviewing
3	Rejected

POST /Api/v1/LLM/chat/completions LLM Chat Completion

Chat completion for the 9 supported language models (DeepSeek / Qwen / GLM / Kimi). The request and response use the OpenAI-compatible format. Set stream=true to receive an SSE streaming response.

Supported Models

deepseek-v4-pro-0813 deepseek-v4-flash-0731 qwen3.8-max qwen3.8-flash qwen3.7-plus qwen3.7-max qwen3.7-flash glm-5.2 kimi-k3

Request Body (JSON)

{
  "model": "qwen3.8-max",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Hello!" }
  ],
  "stream": false,
  "temperature": 0.7,
  "top_p": 0.8,
  "max_tokens": 1024
}

Parameter Description

Field	Type	Required	Description
model	string	Yes	Model name (one of the supported models above)
messages	array	Yes	Conversation messages: `{"role": "system"\|"user"\|"assistant", "content": "..."}`
stream	bool	No	Default `false`; `true` returns an SSE streaming response
temperature	number	No	Sampling temperature, range [0, 2)
top_p	number	No	Nucleus sampling threshold (0, 1]
max_tokens	int	No	Maximum number of tokens to generate
max_completion_tokens	int	No	Maximum total output tokens (thinking + answer), recommended for thinking models
stop	string/array	No	Stop condition: a string or an array of strings / token ids
presence_penalty	number	No	Presence penalty, range [-2.0, 2.0]
frequency_penalty	number	No	Frequency penalty, range [-2.0, 2.0]
n	int	No	Number of answers to generate, 1~4 (qwen-plus only)
seed	int	No	Random seed
tools	array	No	Tools (function calling), cannot be used together with `stream=true`
stream_options	object	No	Stream options, e.g. `{"include_usage": true}`. Only valid when `stream=true`
enable_thinking	bool	No	Whether to enable deep thinking mode
thinking_budget	int	No	Thinking budget (thinking_budget, range 1~32768, larger = deeper thinking)

Non-streaming response (stream=false)

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1716430652,
  "model": "qwen3.8-max",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "Hello! How can I help you today?" },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 10, "completion_tokens": 12, "total_tokens": 22 }
}

Streaming response (SSE, stream=true)

When stream=true, the server returns data:-prefixed JSON chunks as text/event-stream; the incremental text is in choices[0].delta.content (thinking text in delta.reasoning_content), ending with data: [DONE].

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1716430652,"model":"qwen3.8-max","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1716430652,"model":"qwen3.8-max","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1716430652,"model":"qwen3.8-max","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1716430652,"model":"qwen3.8-max","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
data: [DONE]

HTTP Status Code Description

Status Code	error.code	Description
401	invalid_api_key	API Key invalid or insufficient permissions
403	invalid_model	Unsupported model
403	invalid_parameters	Incorrect parameters
429	rate_limit_exceeded	Too many requests, please try again later
500	internal_error	Internal server error

APIKey Management

APIKeys must be created and managed on the API Keys page after logging in.