> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Fal.ai

> The generative media platform for developers with 600+ AI models for image, video, voice, and audio generation

![Fal.ai logo](https://mintcdn.com/composio-preview/r7CO9m4_UWMVFnU7/images/toolkits/fal_ai.svg?fit=max\&auto=format\&n=r7CO9m4_UWMVFnU7\&q=85\&s=2660e28a1e82c4e163c2a617ae538fad)

* **Category:** media generation
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 13
* **Triggers:** 0
* **Slug:** `FAL_AI`
* **Version:** 20261101\_00
* **Instant:** Supported on the latest version. Support varies by tool.

## Tools

> [accordion] Cancel Queue Request
>
> **Slug:** `FAL_AI_CANCEL_QUEUE_REQUEST`
>
> Request cancellation of a queued or in-progress fal.ai job using your own fal account. Queued jobs are removed; for jobs already running, fal sends a cancellation signal and the model determines how to stop.
>
> #### Input Parameters
>
> **model\_id** `string` *required*
>
> The model identifier in namespace/name format (e.g., 'fal-ai/flux', 'fal-ai/fast-sdxl')
>
> **request\_id** `string` *required*
>
> The unique identifier of the queued request to cancel
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Estimate Pricing
>
> **Slug:** `FAL_AI_ESTIMATE_PRICING`
>
> Estimate expected costs for API calls or unit-based usage across one or more fal.ai model endpoints using your own fal account.
>
> #### Input Parameters
>
> **endpoints** `object` *required*
>
> Map of endpoint IDs (e.g., 'fal-ai/flux/dev') to their quantity specifications. Use call\_quantity for historical\_api\_price or unit\_quantity for unit\_price
>
> **estimate\_type** `string ("historical_api_price" | "unit_price")` *required*
>
> Estimation method: 'historical\_api\_price' for call-based estimates or 'unit\_price' for unit-based estimates
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get JWKS for Webhook Verification
>
> **Slug:** `FAL_AI_GET_JWKS`
>
> Retrieve the JSON Web Key Set used for fal.ai webhook signature verification using your own fal account. The keys are cacheable but should be refreshed at least every 24 hours.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Models
>
> **Slug:** `FAL_AI_GET_MODELS`
>
> Discover and search fal.ai model endpoints using your own fal account. Find models by ID, category or query, with pagination and optional OpenAPI schema expansion.
>
> #### Input Parameters
>
> **q** `string`
>
> Free-text search query. Filters models by name, description, or category. Use for broad text-based searches.
>
> **limit** `integer`
>
> Maximum number of items to return. Actual maximum depends on query type.
>
> **cursor** `string`
>
> Pagination cursor from previous response. Encodes page number for fetching next page.
>
> **expand** `string`
>
> Fields to expand in response. Supports 'openapi-3.0' to include full OpenAPI schema for each model.
>
> **status** `string ("active" | "deprecated")`
>
> Filter models by status. Use 'active' for currently supported models or 'deprecated' for outdated ones. Omit to include all statuses.
>
> **category** `string`
>
> Filter models by specific category. Use exact category names like 'text-to-image', 'image-to-video', etc.
>
> **endpoint\_id** `string`
>
> Specific endpoint ID(s) to retrieve. Accepts a single string or array of strings (1-50 models). Use to filter models by their unique identifiers.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Model Pricing
>
> **Slug:** `FAL_AI_GET_PRICING`
>
> Retrieve unit pricing for specific fal.ai model endpoints using your own fal account, including unit price, billing unit and currency.
>
> #### Input Parameters
>
> **endpoint\_id** `string` *required*
>
> Filter by specific endpoint ID(s). Accepts 1-50 endpoint IDs. Can be a single endpoint ID string or a list of endpoint IDs. Examples: 'fal-ai/flux/dev' or \['fal-ai/flux/dev', 'fal-ai/flux/pro']
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Queue Request Result
>
> **Slug:** `FAL_AI_GET_QUEUE_REQUEST_RESULT`
>
> Tool to retrieve the final result of a completed queue request. Use when you need to get the output of a model request that was submitted to the queue and has finished processing. Checks the job once without blocking and returns its pending or failed status or the completed output. With your own fal account it returns the completed output. Free; no extra charge.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0 per request
>
> #### Input Parameters
>
> **model\_id** `string` *required*
>
> Use exactly the same model\_id you supplied to Submit Async Job. Do not shorten the model path.
>
> **request\_id** `string` *required*
>
> Copy the complete request\_id returned by Submit Async Job unchanged, using the same user and project. Without your own fal account this is a signed ID with a model prefix; do not replace it with a raw fal request UUID. With your own fal account, use the fal request UUID.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Model Requests
>
> **Slug:** `FAL_AI_LIST_MODEL_REQUESTS`
>
> List recent fal.ai model requests with filters and cursor pagination using your own fal account.
>
> #### Input Parameters
>
> **end** `string`
>
> Exclusive ISO 8601 date or timestamp at which to end the request history.
>
> **limit** `integer`
>
> Number of requests to return per page, from 1 to 100.
>
> **start** `string`
>
> Inclusive ISO 8601 date or timestamp at which to begin the request history.
>
> **cursor** `string`
>
> Pagination cursor returned in next\_cursor by a previous call.
>
> **expand** `string`
>
> Set to payloads, or a list containing payloads, to include request input and output payloads.
>
> **status** `string ("success" | "error" | "user_error")`
>
> Return only requests with this outcome.
>
> **sort\_by** `string ("ended_at" | "duration")`
>
> Sort requests by completion time or duration.
>
> **request\_id** `string`
>
> Return a specific request UUID.
>
> **endpoint\_id** `string` *required*
>
> One endpoint ID or a list of 1-50 endpoint IDs whose requests should be returned.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Check Queue Request Status
>
> **Slug:** `FAL_AI_QUEUE_GET_STATUS`
>
> Check the status of a queued fal.ai request using your own fal account. The response may include queue position and, when requested, logs.
>
> #### Input Parameters
>
> **logs** `integer`
>
> Set to 1 to enable log retrieval in the response; disabled by default for performance
>
> **model\_id** `string` *required*
>
> Model identifier in namespace/name format (e.g., 'fal-ai/fast-sdxl')
>
> **request\_id** `string` *required*
>
> Unique identifier returned after submitting a request
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Stream Request Status Updates
>
> **Slug:** `FAL_AI_QUEUE_GET_STATUS_STREAM`
>
> Collect SSE status updates for a queued fal.ai request using your own fal account. The action returns the collected updates after the stream ends.
>
> #### Input Parameters
>
> **logs** `integer`
>
> Set to 1 to include detailed logging information in the stream, 0 or omit to exclude logs
>
> **model\_id** `string` *required*
>
> The model identifier (e.g., 'fal-ai/fast-lightning-sdxl')
>
> **request\_id** `string` *required*
>
> The unique identifier returned when submitting a request
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Run Model (Sync)
>
> **Slug:** `FAL_AI_RUN_MODEL_SYNC`
>
> Run a fal.ai model synchronously using your own fal account and return its model-specific output. The call performs paid inference and waits for the response.
>
> #### Input Parameters
>
> **input** `object` *required*
>
> Model-specific input payload posted as the JSON request body. Fields depend on the chosen model — for example image generation models typically expect a 'prompt' (and optionally 'image\_size', 'num\_inference\_steps', etc.). Refer to the model's OpenAPI schema (see GET\_MODELS with expand=openapi-3.0) for the full field list.
>
> **model\_id** `string` *required*
>
> The model identifier in namespace/name format (e.g., 'fal-ai/flux/schnell', 'fal-ai/fast-sdxl'). Slashes in the model id are preserved in the URL path.
>
> **runner\_hint** `string`
>
> Optional session affinity hint to route subsequent requests to the same runner. Sent as the 'X-Fal-Runner-Hint' header.
>
> **timeout\_seconds** `integer`
>
> Optional server-side deadline in seconds to start processing, including queue wait (does not limit running inference). Sent as the 'X-Fal-Request-Start-Timeout' header.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Submit Async Inference Job
>
> **Slug:** `FAL_AI_SUBMIT_ASYNC_JOB`
>
> Start image, text-to-video, image-to-video or 3D generation and return a job ID immediately. Without your own fal account, choose one of the 19 model\_id/input examples, omit the five queue options that need your own fal account (webhook\_url, priority, timeout\_seconds, runner\_hint, no\_retry), then save request\_id and use GET\_QUEUE\_REQUEST\_RESULT with the same model\_id, user and complete ID to check progress and retrieve the output. The exact Sunburst route supports text-to-image only; Flare, GPT Image 2 and image editing are not substitutes. Status/result retrieval is included in the accepted-job price. Without your own fal account, automatic retries are disabled; do not submit a duplicate after an uncertain response. Other queue helpers, cancellation, streams and webhooks are available only with your own fal account.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** Images from \$0.003; videos from \$0.04 per second or \$0.19 per clip; \$2 max per job.
>
> #### Input Parameters
>
> **input** `object` *required*
>
> Model settings. Use a complete example for your model and change the prompt or image\_url. Schnell: set image\_size=\{width:512,height:512}, num\_images=1, num\_inference\_steps=1..4, enable\_safety\_checker=true and output\_format=png or jpeg. Wan text-to-video and image-to-video: choose resolution=480p/580p/720p and num\_frames=17/33/49/65/81; explicitly set frames\_per\_second=16, aspect\_ratio=16:9, num\_inference\_steps=27, both safety checks=true, enable\_prompt\_expansion=false, interpolator\_model=none and num\_interpolated\_frames=0. Image-to-video also requires a publicly accessible HTTPS image\_url. Trellis requires image\_url, ss\_guidance\_strength=7.5, ss\_sampling\_steps=12, slat\_guidance\_strength=3, slat\_sampling\_steps=12, mesh\_simplify=0.95 and texture\_size=1024. For the added models, copy the complete paired example: MiniMax requires its prompt optimizer setting and duration where offered; Nano Banana requires one image, resolution and its fixed safety/add-on settings; Kling requires duration and safety settings; Kling 3 also requires start\_image\_url and generate\_audio; Trellis 2 requires image\_url and resolution. Seedream Lite requires auto\_2K, num\_images=1, max\_images=1, safety enabled and sync/BytePlus URLs disabled; Pro requires one 1024x1024 or 2048x2048 image, jpeg/png, standard prompt enhancement, safety enabled and sync disabled. GPT Image 2.5 Sunburst requires exact 1024x1024 size, opaque background, low quality, one PNG, sync\_mode=false and safety enabled; editing, compression and other fields are rejected. Standard Seedance 2.0 text-to-video requires duration=4, resolution=720p, aspect\_ratio=16:9, bitrate\_mode=standard and codec=auto; generate\_audio explicitly selects native audio at no price difference. Its documented schema has no safety option, so omit safety fields. Without your own fal account these settings are mandatory and unlisted fields or paid add-ons are rejected. With your own fal account, any of the selected model's input fields are accepted.
>
> **model\_id** `string` *required*
>
> Without your own fal account, only the 19 model IDs are accepted listed in the complete paired examples: Schnell, Wan, Trellis, MiniMax Image-01/Hailuo 2.3, Nano Banana 2, Kling 2.5 Turbo Pro, Kling 3 Pro and Trellis 2, Seedream 5.0 Lite and Pro, plus exact GPT Image 2.5 Sunburst text-to-image and standard Seedance 2.0 text-to-video. Flare, GPT Image 2, Sunburst editing and standalone TTS/audio models are not admitted; Kling 3 and Seedance 2.0 native video audio are supported. With your own fal account, any model identifier in namespace/name format is accepted (e.g., 'fal-ai/flux/schnell', 'fal-ai/fast-sdxl'). Slashes in the model id are preserved in the URL path.
>
> **no\_retry** `boolean`
>
> Only available with your own fal account; otherwise omit it (retries are disabled automatically). Set to true to disable fal.ai's automatic retries on transient runner errors. Sent as the 'X-Fal-No-Retry' header when true.
>
> **priority** `string ("normal" | "low")`
>
> Only available with your own fal account; otherwise omit it. Optional queue priority hint. Sent as the 'X-Fal-Queue-Priority' header.
>
> **runner\_hint** `string`
>
> Only available with your own fal account; otherwise omit it. Optional session affinity hint to route subsequent requests to the same runner. Sent as the 'X-Fal-Runner-Hint' header.
>
> **webhook\_url** `string`
>
> Only available with your own fal account; otherwise omit it. Optional URL to receive a POST callback when the job completes, instead of (or in addition to) polling. Sent to fal.ai as the 'fal\_webhook' query parameter.
>
> **timeout\_seconds** `integer`
>
> Only available with your own fal account; otherwise omit it. Maximum seconds to wait for processing to start, including queue wait; does not limit running inference. Sent as X-Fal-Request-Start-Timeout.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Subscribe to Async Inference Job
>
> **Slug:** `FAL_AI_SUBSCRIBE_ASYNC_JOB`
>
> Submit a fal.ai inference job using your own fal account, poll until it completes or the wait deadline is reached, and return the final result. A timeout does not cancel the underlying job.
>
> #### Input Parameters
>
> **input** `object` *required*
>
> Model-specific input payload posted as the JSON request body.
>
> **model\_id** `string` *required*
>
> The model identifier in namespace/name format (e.g., 'fal-ai/flux/schnell'). Slashes are preserved in the URL path.
>
> **priority** `string ("normal" | "low")`
>
> Optional queue priority hint for the initial submission ('X-Fal-Queue-Priority').
>
> **runner\_hint** `string`
>
> Optional session-affinity hint for the initial submission ('X-Fal-Runner-Hint').
>
> **include\_logs** `boolean`
>
> If true, request runner logs along with each status poll (forwarded to fal.ai as ?logs=1).
>
> **timeout\_seconds** `integer`
>
> Optional server-side deadline in seconds to start processing, including queue wait (does not limit running inference) for the initial submission ('X-Fal-Request-Start-Timeout').
>
> **max\_wait\_seconds** `number`
>
> Hard deadline. If the job hasn't transitioned to COMPLETED within this many seconds the action raises a timeout error (the underlying job is NOT cancelled). Capped at 900 to keep the action well below Composio's serverless execution limits.
>
> **poll\_interval\_seconds** `number`
>
> Seconds between status polls while the job is IN\_QUEUE or IN\_PROGRESS.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Upload Input File
>
> **Slug:** `FAL_AI_UPLOAD_FILE`
>
> Upload an input media file to fal.ai storage using your own fal account and return its access URL for use as a model input.
>
> #### Input Parameters
>
> **file** `object` *required*
>
> File to upload to fal.ai storage. The returned access\_url can then be passed as a model input field (e.g., 'image\_url', 'audio\_url', 'video\_url'). Supported types include images (jpg, jpeg, png, gif, webp), videos (mp4, mov, webm), and audio (mp3, wav, flac).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
