Integration

fal.ai integration

fal.ai runs hosted generative AI models (image, video, audio, speech, 3D, LLM) through a durable queue, and exposes its Platform API around them. Submit a billed model run, poll its status and fetch or cancel the result; search the model catalog and read each model's input schema and pricing, estimate costs; read usage, billing events, analytics and request history; manage the Assets library (collections, characters and entities, tags, favorites, uploads), CDN file access and storage settings, saved workflows, serverless apps (queues, logs, files, revisions) and compute instances. API key management, live log streaming, Prometheus metrics, CSV reports and multipart file upload are not exposed. Authentication is a fal API key sent as Authorization: Key <key>; each tool says which key presets (API, READONLY, BILLING, FULL...) may call it.

Connect fal.ai How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in fal.ai.Built from the 82 fal.ai tools below, on the connection you add once.

Common fal.ai use cases

image generation
video generation
speech and audio generation

What you can do with fal.ai

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Tag, 6 operations

create_asset_tagCreate asset tagPOSTCreate asset tag for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.
delete_asset_tagDelete asset tagDELETEDelete asset tag for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.
list_asset_tagsList asset tagsGETList asset tags for the authenticated user's fal Assets library. Key preset: API, SERVERLESS, READONLY or FULL.
list_asset_tags_for_assetList asset tags for assetGETList tags for an asset by asset ID; a vector ID is also accepted. Assets without a live catalog record return an empty tag list. Key preset: API, SERVERLESS, READONLY or FULL.
set_asset_tagsSet asset tagsPUTSet tags for an asset. Provide a request ID or vector ID; unresolved references are materialized before tag state is added. Key preset: API, SERVERLESS or FULL.
update_asset_tagUpdate asset tagPATCHUpdate asset tag for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.

Asset, 5 operations

add_asset_to_collectionAdd asset to collectionPOSTAdd an asset to a manual or character collection. Provide exactly one asset ID, request ID, or vector ID. Unresolved request and vector IDs are materialized before membership is added. Key preset: API, SERVERLESS or FULL.
get_assetGet assetGETGet an asset from the authenticated user's fal Assets library by asset ID; a vector ID is also accepted. Key preset: API, SERVERLESS, READONLY or FULL.
list_asset_collection_assetsList asset collection assetsGETBrowse assets in a collection for the authenticated user's fal Assets library. Key preset: API, SERVERLESS, READONLY or FULL.
list_assetsList assetsGETBrowse and semantically search fal Assets across all media, uploads, favorites, collections, tags, and character references. Key preset: API, SERVERLESS, READONLY or FULL.
remove_asset_from_collectionRemove asset from collectionDELETERemove an asset from a manual or character collection. Provide exactly one asset ID, request ID, or vector ID. For character collections, this removes the explicit smart-entity link. Key preset: API, SERVERLESS or FULL.

Character, 5 operations

create_asset_characterCreate asset characterPOSTCreate an asset character for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.
delete_asset_characterDelete asset characterDELETEDelete asset character for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.
get_asset_characterGet asset characterGETGet asset character for the authenticated user's fal Assets library. Key preset: API, SERVERLESS, READONLY or FULL.
list_asset_charactersList asset charactersGETList asset characters for the authenticated user's fal Assets library. Key preset: API, SERVERLESS, READONLY or FULL.
update_asset_characterUpdate asset characterPATCHUpdate an asset character for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.

Collection, 5 operations

create_asset_collectionCreate asset collectionPOSTCreate asset collection for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.
delete_asset_collectionDelete asset collectionDELETEDelete asset collection for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.
get_asset_collectionGet asset collectionGETGet asset collection for the authenticated user's fal Assets library. Key preset: API, SERVERLESS, READONLY or FULL.
list_asset_collectionsList asset collectionsGETList asset collections for the authenticated user's fal Assets library. Key preset: API, SERVERLESS, READONLY or FULL.
update_asset_collectionUpdate asset collectionPATCHUpdate asset collection for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.

Entity, 5 operations

create_asset_entityCreate asset entityPOSTCreate a reusable character, prop, environment, style, or scene in fal Assets. The entity is available to @mention in the UI and agent. Key preset: API, SERVERLESS or FULL.
delete_asset_entityDelete asset entityDELETEDelete a saved entity from the authenticated account. Its reference assets are not deleted. Key preset: API, SERVERLESS or FULL.
get_asset_entityGet asset entityGETGet a saved entity's type, @mention handle, visual description, and defining reference images. Only entities belonging to the authenticated account are accessible. Key preset: API, SERVERLESS, READONLY or FULL.
list_asset_entitiesList asset entitiesGETList saved characters, props, environments, styles, and scenes in the authenticated account. Returns their @mention handles and defining reference images. Key preset: API, SERVERLESS, READONLY or FULL.
update_asset_entityUpdate asset entityPATCHUpdate a saved entity without recreating it. Omitted fields stay unchanged; reference_images replaces the defining reference set. Entity types cannot be changed. Key preset: API, SERVERLESS or FULL.

Model request, 4 operations

cancel_requestCancel requestPUTCancels a request: IN_QUEUE it is removed and never runs (status OK); IN_PROGRESS the runner is asked to stop and may still finish (CANCELLATION_REQUESTED). Fails with ALREADY_COMPLETED or NOT_FOUND. Key preset: API, SERVERLESS or FULL.
get_request_resultGet request resultGETReturns the output of a COMPLETED request, under result. Its shape is model-specific: image models return images (url, width, height), video models a video object, audio models audio_url or audio. Key preset: API, SERVERLESS or FULL.
get_request_statusGet request statusGETReturns the queue state of a submitted request: IN_QUEUE with its position, IN_PROGRESS, or COMPLETED (with error and error_type if it failed). Call get_request_result once COMPLETED. Key preset: API, SERVERLESS or FULL.
submit_model_requestSubmit model requestPOSTQueues a BILLED run of a fal model (model_id) with its input and returns request_id at once. Poll get_request_status with the owner/app part of model_id, then fetch the output with get_request_result. Key preset: API, SERVERLESS or FULL.

Favorite, 3 operations

favorite_assetFavorite assetPOSTFavorite an asset. Provide a request ID or vector ID; unresolved references are materialized before favorite state is added. Key preset: API, SERVERLESS or FULL.
favorite_asset_characterFavorite asset characterPOSTFavorite an asset character for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.
favorite_asset_collectionFavorite asset collectionPOSTFavorite an asset collection for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.

Instance, 3 operations

delete_compute_instanceDelete compute instanceDELETEPermanently deletes one of your compute instances by id. Irreversible. Key preset: COMPUTE or FULL.
get_compute_instanceGet compute instanceGETRetrieves detailed information about a specific compute instance by its ID. Key preset: COMPUTE, READONLY or FULL.
list_compute_instancesList compute instancesGETReturns a list of all compute instances belonging to the authenticated user's workspace. Key preset: COMPUTE, READONLY or FULL.

Unfavorite, 3 operations

unfavorite_assetUnfavorite assetPOSTUnfavorite an asset by request ID or vector ID. Key preset: API, SERVERLESS or FULL.
unfavorite_asset_characterUnfavorite asset characterPOSTUnfavorite an asset character for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.
unfavorite_asset_collectionUnfavorite asset collectionPOSTUnfavorite an asset collection for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.

Usage, 3 operations

get_model_usageGet model usageGETReturns paginated usage records for your workspace with filters for endpoint, user, date range, and auth method. Key preset: BILLING or FULL.
get_organization_usageGet organization usageGETReturns paginated usage records across all teams and product lines in your organization, with each record attributed to a specific team via the username field and a product line via the product field. Key preset: BILLING or FULL.
get_serverless_usageGet serverless usageGETTime-bucketed, aggregated serverless compute usage for your own account, the machine-seconds your deployed serverless apps consumed, priced with your machine prices and net of discounts. Key preset: BILLING, READONLY or FULL.

Workflow, 3 operations

create_workflowCreate workflowPOSTCreate a new workflow owned by the authenticated user. Key preset: SERVERLESS or FULL.
get_workflowGet workflowGETGet detailed information about a specific workflow, including its full contents/definition. Key preset: API, SERVERLESS, READONLY or FULL.
list_workflowsList workflowsGETList workflows for the authenticated user with optional search and filtering. Key preset: API, SERVERLESS, READONLY or FULL.

Acl, 2 operations

get_storage_file_aclGet storage file aclGETReturns the Access Control List currently applied to a fal CDN file. The ACL consists of a default decision (allow, forbid, or hide) plus optional per-user rules that override the default. Key preset: API, SERVERLESS, READONLY or FULL.
set_storage_file_aclSet storage file aclPUTReplaces the Access Control List of a fal CDN file. The ACL consists of a default decision (allow, forbid, or hide) plus optional per-user rules that override the default. Key preset: API, SERVERLESS or FULL.

Analytics, 2 operations

get_model_analyticsGet model analyticsGETReturns time-bucketed metrics for model endpoints you call (request counts, success and error rates, latency percentiles); pick the metrics with expand. Key preset: API, SERVERLESS, READONLY or FULL.
get_serverless_analyticsGet serverless analyticsGETReturns time-bucketed metrics for your own serverless app endpoints across all inbound traffic (counts, error rates, latency); pick metrics with expand. You must own every endpoint_id. Key preset: API, SERVERLESS, COMPUTE, READONLY or FULL.

Assign, 2 operations

assign_asset_tagAssign asset tagPOSTAssign a tag to an asset. Provide a request ID or vector ID; unresolved references are materialized before tag state is added. Key preset: API, SERVERLESS or FULL.
unassign_asset_tagUnassign asset tagDELETEUnassign a tag from an asset by request ID or vector ID. Key preset: API, SERVERLESS or FULL.

Billing event, 2 operations

list_billing_eventsList billing eventsGETReturns paginated individual billing event records with filters for endpoint and date range. Key preset: BILLING or FULL.
list_organization_billing_eventsList organization billing eventsGETReturns paginated individual billing event records across all teams in your organization, with each record attributed to a specific team via the username field. Key preset: BILLING or FULL.

By endpoint, 2 operations

list_requests_by_endpointList requests by endpointGETLists requests for one or more endpoints (same endpoint_id style as usage/explore: comma-separated or repeated query params, up to 50 IDs). Key preset: API, SERVERLESS, READONLY or FULL.
list_serverless_requests_by_endpointList serverless requests by endpointGETLists requests for one or more endpoints owned by the authenticated user. Use repeated or comma-separated endpoint_id (same as other platform list APIs). Key preset: API, SERVERLESS, READONLY or FULL.

History, 2 operations

get_serverless_runner_historyGet serverless runner historyGETReturns historical runner counts by state (running, idle, pending, draining) for an application, bucketed over time. Key preset: SERVERLESS, DEPLOY, READONLY or FULL.
list_serverless_logsList serverless logsPOSTReturns paginated historical logs that match the provided filters. Key preset: SERVERLESS, DEPLOY, READONLY or FULL.

List, 2 operations

list_serverless_directoryList serverless directoryGETLists files and folders within the specified directory path. Key preset: SERVERLESS, DEPLOY, READONLY or FULL.
list_serverless_filesList serverless filesGETLists files and folders in the root of your project storage. Key preset: SERVERLESS, DEPLOY, READONLY or FULL.

Queue, 2 operations

flush_serverless_app_queueFlush serverless app queueDELETEPermanently removes every pending request from one of your serverless apps' queue; those requests never run. Irreversible. Key preset: SERVERLESS or FULL.
get_serverless_app_queueGet serverless app queueGETRetrieves the current queue size for a specific application. Key preset: SERVERLESS, READONLY or FULL.

Settings, 2 operations

get_storage_settingsGet storage settingsGETReturns the storage lifecycle settings for new fal CDN uploads: expiration_duration_seconds (null: no auto-expiry) and initial_acl (null: the public system default). Key preset: API, SERVERLESS, DEPLOY, COMPUTE, BILLING, READONLY or FULL.
update_storage_settingsUpdate storage settingsPUTReplaces the account storage lifecycle settings for newly uploaded fal CDN files: send the full configuration, an omitted or null field is reset to the system default. Key preset: FULL.

App, 1 operation

list_serverless_appsList serverless appsGETLists the serverless applications owned by the authenticated account, with the configuration needed for follow-up calls. Key preset: SERVERLESS, DEPLOY, READONLY or FULL.

Billing, 1 operation

get_account_billingGet account billingGETReturns billing information for the authenticated account. Use the expand parameter to include additional details. Key preset: BILLING, READONLY or FULL.

Estimate, 1 operation

estimate_model_costEstimate model costPOSTEstimates the cost of planned usage, free of charge: estimate_type historical_api_price prices a number of calls per endpoint, unit_price prices a number of billing units (images, seconds). Any fal key works.

Event, 1 operation

list_serverless_app_eventsList serverless app eventsGETReturns the operational event history for an application: deployments, configuration changes, and runner lifecycle transitions (started, failed, draining, etc.), newest first. Key preset: SERVERLESS, DEPLOY, READONLY or FULL.

File, 1 operation

download_serverless_fileDownload serverless fileGETDownloads a file by its path. Proxies the underlying storage response. Key preset: SERVERLESS, DEPLOY, READONLY or FULL.

Hierarchy, 1 operation

get_asset_collection_hierarchyGet asset collection hierarchyGETGet the nested subtree rooted at an asset collection, plus its ancestor collections ordered from the top level down to its direct parent. Key preset: API, SERVERLESS, READONLY or FULL.

Insight, 1 operation

get_model_insightsGet model insightsGETBeta: finds published guidance on which fal models suit a task (q) or given endpoint_ids, with latency and quality evidence. Results may change. Any fal key works.

Lineage, 1 operation

get_asset_lineageGet asset lineageGETReturns how an asset was derived: its input assets, the generation requests on the way and referenced entities, up to depth levels. Deleted or expired ancestors stay flagged as tombstones. Key preset: API, SERVERLESS, READONLY or FULL.

Meta, 1 operation

get_platform_metadataGet platform metadataGETReturns platform metadata including webhook IP ranges for allowlisting. Works without a key.

Model, 1 operation

list_modelsList modelsGETLists or searches fal model endpoints: no filter lists all, endpoint_id fetches given models, q / category / status search. Each endpoint_id is the model_id submit_model_request takes. expand=openapi-3.0 adds the input schema. Works without a key.

Move, 1 operation

move_asset_collectionMove asset collectionPOSTMove a manual asset collection under another collection, or to the top level. Only manual collections can be moved or act as folders; nesting is limited to 5 levels deep and cannot create a cycle. Key preset: API, SERVERLESS or FULL.

Payload, 1 operation

delete_request_payloadsDelete request payloadsDELETEPermanently deletes the stored input and output payloads of one request and its output CDN files (input files are kept). Irreversible. Key preset: FULL.

Pricing, 1 operation

get_model_pricingGet model pricingGETReturns unit pricing for requested endpoint IDs. Most models use output-based pricing (e.g., per image/video with proportional adjustments for resolution/length). Some models use GPU-based pricing depending on architecture. Any fal key works.

Revision, 1 operation

list_serverless_app_revisionsList serverless app revisionsGETLists the deployed revisions of one of your serverless apps, newest first, with creation time, whether it serves traffic and a deployment status from the last 30 days. Key preset: SERVERLESS, DEPLOY, READONLY or FULL.

Search, 1 operation

search_requestsSearch requestsGETSearches your request history by text (query), by similar image or video (image_url, video_url), or filters it by endpoint and API-key or playground origin. Returns request ids with their outputs. Key preset: API, SERVERLESS, READONLY or FULL.

Sign, 1 operation

sign_storage_file_urlSign storage file urlPOSTCreates a signed URL that grants temporary access to a fal CDN file, regardless of its ACL. Useful for sharing access-restricted files. The signature is valid for expiration_seconds (up to 7 days). Key preset: API, SERVERLESS, READONLY or FULL.

Team, 1 operation

list_organization_teamsList organization teamsGETLists the teams of your organization. Enterprise only: must be called with a key on the organization's root team. Key preset: BILLING or FULL.

Upload, 1 operation

upload_assetUpload assetPOSTUpload asset for the authenticated user's fal Assets library. Key preset: API, SERVERLESS or FULL.

Url, 1 operation

upload_serverless_file_from_urlUpload serverless file from urlPOSTCreates a new file at the target path by downloading it from the provided URL. Key preset: SERVERLESS, DEPLOY or FULL.

Use fal.ai from Claude Code, Cursor or Codex

Connect fal.ai in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its fal.ai operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect fal.ai

Create your workspace
Sign up free. Nothing to install.
Connect fal.ai once
Add your fal.ai connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

fal.ai integration FAQ

What can you do with the fal.ai integration?

LiveContext exposes 82 operations on fal.ai, covering tag, asset, character and collection. Common uses include image generation, video generation and speech and audio generation.