Models (Read-Only)
list-models
Browse and search available AI models on the ModelsLab platform.
Filter by product: imagen, videofusion, audiogen, llmaster, threedverse
Filter by model category (e.g., stable_diffusion, flux, llm, video)
Filter by subcategory (e.g., lora, controlnet, checkpoint)
Filter by provider (e.g., modelslab, civitai)
Search by name, ID, description, or tags
Filter models that have ALL specified tags
false to exclude NSFW, true to include. Defaults to user preference
Sort order: recommended (default), latest, most-used
Max results (1-100). Default: 20
list-providers
List all model providers with model counts.
Filter by product: imagen, videofusion, audiogen, llmaster, threedverse
Image Generation
text-to-image
Generate images from text prompts.
Model ID (e.g., flux-dev, sdxl)
Text description of the image
What to avoid in the image
Aspect ratio (e.g., 1:1, 16:9, 9:16)
Webhook URL for completion notification
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 for transformation
How to transform the image
Input image URL or base64 string
What to avoid in the output
Transformation strength (0-1). Higher = more change
inpaint-image
Edit specific areas of images using masks.
What to paint in the masked area
Input image URL or base64
Mask image (white = edit, black = preserve)
Transformation strength (0-1)
fetch-image
Retrieve the status and results of an image generation request.
Request ID from a previous generation call
Video Generation
text-to-video
Generate videos from text descriptions.
Model ID for video generation
Text description of the video
Aspect ratio (e.g., 16:9, 9:16)
Duration in seconds (min 4)
Generate in portrait orientation
Keep camera position fixed
Use AI to enhance the prompt
Generate audio for the video
image-to-video
Animate static images into videos.
Model ID for video generation
Input image URL or base64
Motion/transformation description
Duration in seconds (min 4)
video-to-video
Transform existing videos with AI.
Model ID for transformation
How to transform the video
Duration in seconds (min 4)
Random seed (0-4294967295)
lip-sync
Sync video with audio for lip movements.
Video URL or base64 containing face
Audio URL or base64 to sync with
motion-control
Control motion in video generation using reference video.
Model ID for motion control
Video for motion reference
Use orientation from image or video
Optional text prompt (max 2500 chars)
std (standard) or pro (professional)
fetch-video
Retrieve the status and results of a video generation request.
Request ID from a previous video generation call
Audio Generation
text-to-speech
Convert text to natural speech audio.
Model ID for text-to-speech
Text to convert to speech
speech-to-text
Transcribe audio to text.
Model ID for transcription
Audio URL or base64 to transcribe
speech-to-speech
Voice conversion and transformation.
Model ID for voice conversion
Audio URL or base64 to transform
sound-generation
Generate sound effects from text descriptions.
Model ID for sound generation
Description of the sound effect
music-generation
Create music from text prompts.
Model ID for music generation
Description of the music to generate
song-extender
Extend existing music tracks.
Model ID for song extension
Audio URL or base64 to extend
Direction for the extension
song-inpaint
Edit specific parts of songs.
Model ID for song inpainting
Audio URL or base64 to edit
What to replace/edit in the song
dubbing
Create dubbed audio content.
Original audio URL or base64
Target language for dubbing
fetch-audio
Retrieve the status and results of an audio generation request.
Request ID from a previous audio generation call
LLM
chat-completion
Chat with AI language models.
Array of message objects with role and content
Maximum tokens to generate