Runs generative image, video, and audio models through a queue-based inference API, Python and JS clients, a CLI, and a hosted MCP server, with webhooks and streaming output.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with fal connected:
- Asynchronous Inference
Use fal to submit model requests to the fal queue: ‹what you need›
- Webhook Callbacks
Use fal to notify a developer endpoint: ‹what you need›
- Streaming Inference
Use fal to get progressive model output: ‹what you need›
Connect it over MCP
{
"mcpServers": {
"fal-ai": {
"url": "https://mcp.fal.ai/mcp-relay"
}
}
}claude mcp add --transport http fal-ai https://mcp.fal.ai/mcp-relay
In Grok, ChatGPT and other assistants, add a custom connector with the address https://mcp.fal.ai/mcp-relay (how, step by step).
It may ask you to sign in to fal or for a key when you add it; the setup guide says which.
Setup guide: fal.ai/docs/documentation/quickstart
Install the CLI
pip install fal
Setup guide: fal.ai/docs/documentation/quickstart
Call the API
https://queue.fal.run
Auth An API key from fal
Setup guide: fal.ai/docs/documentation/quickstart
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APICLIMCP
- Auth
- API Key
- Skills
- 4
Skills
Asynchronous Inference
Submits model requests to the fal queue, then polls status or fetches results when long-running generations complete.
Webhook Callbacks
Notifies a developer endpoint when a queued request finishes so applications avoid polling for generation results.
Streaming Inference
Returns progressive model output as it is generated, with WebSocket and realtime endpoints for interactive use cases.
Hosted MCP Server
Lets AI assistants search models, check schemas and pricing, run inference, and upload files via mcp.fal.ai.
