Skip to main content

​
Models (Read-Only)

​
list-models

Browse and search available AI models on the ModelsLab platform.
​
feature
string
Filter by product: imagen, videofusion, audiogen, llmaster, threedverse
​
category
string
Filter by model category (e.g., stable_diffusion, flux, llm, video)
​
subcategory
string
Filter by subcategory (e.g., lora, controlnet, checkpoint)
​
provider
string
Filter by provider (e.g., modelslab, civitai)
​
search
string
Search by name, ID, description, or tags
​
tags
array
Filter models that have ALL specified tags
​
nsfw
boolean
false to exclude NSFW, true to include. Defaults to user preference
​
sort
string
Sort order: recommended (default), latest, most-used
​
limit
integer
Max results (1-100). Default: 20
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "list-models",
    "arguments": {
      "feature": "imagen",
      "search": "realistic",
      "limit": 5
    }
  }
}

​
list-providers

List all model providers with model counts.
​
feature
string
Filter by product: imagen, videofusion, audiogen, llmaster, threedverse
​
category
string
Filter by model category

​
Image Generation

​
text-to-image

Generate images from text prompts.
​
model_id
string
required
Model ID (e.g., flux-dev, sdxl)
​
prompt
string
required
Text description of the image
​
negative_prompt
string
What to avoid in the image
​
width
integer
default:"1024"
Image width (512-1024)
​
height
integer
default:"1024"
Image height (512-1024)
​
aspect_ratio
string
Aspect ratio (e.g., 1:1, 16:9, 9:16)
​
samples
integer
default:"1"
Number of images (1-4)
​
webhook
string
Webhook URL for completion notification
​
track_id
string
Custom tracking ID
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "text-to-image",
    "arguments": {
      "model_id": "flux-dev",
      "prompt": "A serene mountain landscape at sunset with a crystal clear lake",
      "negative_prompt": "blurry, low quality",
      "width": 1024,
      "height": 768,
      "samples": 1
    }
  }
}
Returns a request ID that can be used with fetch-image to retrieve results.

​
image-to-image

Transform existing images based on text prompts.
​
model_id
string
required
Model ID for transformation
​
prompt
string
required
How to transform the image
​
init_image
string
required
Input image URL or base64 string
​
negative_prompt
string
What to avoid in the output
​
width
integer
Output width (512-1024)
​
height
integer
Output height (512-1024)
​
aspect_ratio
string
Output aspect ratio
​
strength
number
Transformation strength (0-1). Higher = more change
​
samples
integer
Number of images (1-4)
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
inpaint-image

Edit specific areas of images using masks.
​
model_id
string
required
Model ID for inpainting
​
prompt
string
required
What to paint in the masked area
​
init_image
string
required
Input image URL or base64
​
mask_image
string
required
Mask image (white = edit, black = preserve)
​
negative_prompt
string
What to avoid
​
strength
number
Transformation strength (0-1)
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
fetch-image

Retrieve the status and results of an image generation request.
​
id
integer
required
Request ID from a previous generation call

​
Video Generation

​
text-to-video

Generate videos from text descriptions.
​
model_id
string
required
Model ID for video generation
​
prompt
string
required
Text description of the video
​
negative_prompt
string
What to avoid
​
width
integer
Video width (512-1024)
​
height
integer
Video height (512-1024)
​
aspect_ratio
string
Aspect ratio (e.g., 16:9, 9:16)
​
duration
integer
Duration in seconds (min 4)
​
fps
integer
Frames per second
​
resolution
string
Output resolution preset
​
portrait
boolean
Generate in portrait orientation
​
camera_fixed
boolean
Keep camera position fixed
​
enhance_prompt
boolean
Use AI to enhance the prompt
​
generate_audio
boolean
Generate audio for the video
​
init_audio
string
Audio URL to sync with
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
image-to-video

Animate static images into videos.
​
model_id
string
required
Model ID for video generation
​
init_image
string
required
Input image URL or base64
​
prompt
string
Motion/transformation description
​
negative_prompt
string
What to avoid
​
aspect_ratio
string
Video aspect ratio
​
duration
integer
Duration in seconds (min 4)
​
resolution
string
Output resolution preset
​
portrait
boolean
Portrait orientation
​
init_audio
string
Audio URL to sync with
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
video-to-video

Transform existing videos with AI.
​
model_id
string
required
Model ID for transformation
​
prompt
string
required
How to transform the video
​
init_video
string
required
Input video URL
​
init_image
string
Optional reference image
​
negative_prompt
string
What to avoid
​
aspect_ratio
string
Output aspect ratio
​
duration
integer
Duration in seconds (min 4)
​
seed
integer
Random seed (0-4294967295)
​
public_figure_threshold
string
auto, low, medium, high
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
lip-sync

Sync video with audio for lip movements.
​
model_id
string
required
Model ID for lip sync
​
init_video
string
required
Video URL or base64 containing face
​
init_audio
string
required
Audio URL or base64 to sync with
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
motion-control

Control motion in video generation using reference video.
​
model_id
string
required
Model ID for motion control
​
init_image
string
required
Character/subject image
​
init_video
string
required
Video for motion reference
​
character_orientation
string
required
Use orientation from image or video
​
prompt
string
Optional text prompt (max 2500 chars)
​
mode
string
std (standard) or pro (professional)
​
keep_original_sound
string
yes or no
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
fetch-video

Retrieve the status and results of a video generation request.
​
id
string
required
Request ID from a previous video generation call

​
Audio Generation

​
text-to-speech

Convert text to natural speech audio.
​
model_id
string
required
Model ID for text-to-speech
​
prompt
string
required
Text to convert to speech
​
voice_id
string
required
Voice ID to use
​
temperature
number
Voice variation (0-1)
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
speech-to-text

Transcribe audio to text.
​
model_id
string
required
Model ID for transcription
​
init_audio
string
required
Audio URL or base64 to transcribe
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
speech-to-speech

Voice conversion and transformation.
​
model_id
string
required
Model ID for voice conversion
​
init_audio
string
required
Audio URL or base64 to transform
​
voice_id
string
required
Target voice ID
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
sound-generation

Generate sound effects from text descriptions.
​
model_id
string
required
Model ID for sound generation
​
prompt
string
required
Description of the sound effect
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
music-generation

Create music from text prompts.
​
model_id
string
required
Model ID for music generation
​
prompt
string
required
Description of the music to generate
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
song-extender

Extend existing music tracks.
​
model_id
string
required
Model ID for song extension
​
init_audio
string
required
Audio URL or base64 to extend
​
prompt
string
Direction for the extension
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
song-inpaint

Edit specific parts of songs.
​
model_id
string
required
Model ID for song inpainting
​
init_audio
string
required
Audio URL or base64 to edit
​
prompt
string
required
What to replace/edit in the song
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
dubbing

Create dubbed audio content.
​
model_id
string
required
Model ID for dubbing
​
init_audio
string
required
Original audio URL or base64
​
target_language
string
required
Target language for dubbing
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID

​
fetch-audio

Retrieve the status and results of an audio generation request.
​
id
string
required
Request ID from a previous audio generation call

​
LLM

​
chat-completion

Chat with AI language models.
​
model_id
string
required
LLM model ID
​
messages
array
required
Array of message objects with role and content
​
temperature
number
Sampling temperature
​
max_tokens
integer
Maximum tokens to generate
​
webhook
string
Webhook URL
​
track_id
string
Custom tracking ID
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "chat-completion",
    "arguments": {
      "model_id": "llama-3",
      "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
      ],
      "temperature": 0.7,
      "max_tokens": 500
    }
  }
}