# fal

> ## Agent Instructions
> fal has two developer products. Model APIs run hosted models through an API key. fal Serverless deploys your own Python apps and models on fal GPUs.
> To call a hosted model, start with the [Quick Start](https://fal.ai/docs/documentation/quickstart.md) and the [Model APIs overview](https://fal.ai/docs/documentation/model-apis/overview.md).
> To deploy your own model with fal Serverless, start with these pages:
> - [Introduction to Serverless](https://fal.ai/docs/documentation/serverless/index.md): What fal Serverless is and the three ways to deploy on it.
> - [Installation & Setup](https://fal.ai/docs/documentation/development/getting-started/installation.md): Install the fal CLI with `pip install fal` and authenticate.
> - [Quick Start](https://fal.ai/docs/documentation/development/getting-started/quick-start.md): Build a Hello World app, test it with `fal run`, and ship it with `fal deploy`.
> - [App Lifecycle](https://fal.ai/docs/documentation/development/app-lifecycle.md): How a `fal.App` goes from code to running runners.
> - [Define Your Endpoints](https://fal.ai/docs/documentation/development/endpoints-overview.md): Structure the API endpoints that your app exposes.
> - [Deploy to Production](https://fal.ai/docs/documentation/deployment/deploy-to-production.md): Persistent URLs, authentication modes, and automatic scaling.
> - [Machine Types](https://fal.ai/docs/documentation/deployment/machine-types.md): Available GPU and CPU machine types and how to choose one.
> - [Pricing](https://fal.ai/docs/documentation/serverless/pricing.md): Per-second billing and the runner states that are billed.
> - [Scaling Parameter Reference](https://fal.ai/docs/documentation/deployment/scale-your-application.md): Parameters that control runners, concurrency, and scale to zero.
> - [Optimizing Cold Starts](https://fal.ai/docs/documentation/serverless/optimizations/optimize-cold-starts.md): Causes of cold starts and ways to make them shorter.
> - [Examples](https://fal.ai/docs/examples/index.md): Complete Serverless apps for image, video, audio, 3D, realtime, and multi-GPU workloads.
> - [Migrating to fal](https://fal.ai/docs/documentation/development/migrating-to-fal.md): Guides to move an existing Docker server or an app from another platform to fal.
> fal Serverless deploys need access that the fal team approves for each account. Request access at https://fal.ai/dashboard/serverless-get-started.

- [Documentation (195 pages)](https://fal.ai/docs/_llms/documentation.md): Documentation for Documentation.

## Examples

- [Examples](https://fal.ai/docs/examples/index.md): Step-by-step tutorials and code examples for building with fal

### Model APIs

- [Generate Images from Text Tutorial](https://fal.ai/docs/examples/image-generation/generate-images-from-text.md)
- [Generate Videos from Image Tutorial](https://fal.ai/docs/examples/video-generation/generate-videos-from-image.md)
- [Convert Speech to Text Tutorial](https://fal.ai/docs/examples/audio-speech/convert-speech-to-text.md)
- [Use LLMs Tutorial](https://fal.ai/docs/examples/integrations/use-llms.md): fal provides an easy-to-use API for generating text using Language Models (LLMs). You can use the `fal-ai/any-llm` endpoint to generate text based on a given prompt and model.
- [Fastest FLUX Endpoint](https://fal.ai/docs/examples/image-generation/fast-flux.md): We believe fal has the fastest FLUX endpoint in the planet. If you can find a faster one, we guarantee to beat it within one week. 🤝
- [Fastest SDXL Endpoint](https://fal.ai/docs/examples/image-generation/fast-sdxl.md): We believe fal has the fastest SDXL endpoint in the planet. If you can find a faster one, we guarantee to beat it within one week. 🤝
- [Custom Workflow UI Tutorial](https://fal.ai/docs/examples/integrations/custom-workflow-ui.md)
- [Using fal within an n8n workflow](https://fal.ai/docs/examples/integrations/n8n.md): This guide will demonstrate, step-by-step, how to use fal within an n8n workflow.
- [Add fal.ai to your Next.js app Integration](https://fal.ai/docs/examples/integrations/nextjs.md)
- [Add fal.ai to your Next.js app Integration](https://fal.ai/docs/examples/integrations/vercel.md)

### Serverless

- [Deploy a Text-to-Image Model](https://fal.ai/docs/examples/image-generation/deploy-text-to-image-model.md)
- [Deploy ComfyUI on fal - Under construction](https://fal.ai/docs/examples/image-generation/run-comfyui-visual.md): This guide is temporarily unavailable while we update it.
- [Deploy a ComfyUI SDXL Turbo App](https://fal.ai/docs/examples/image-generation/deploy-comfyui-server.md): Build a serverless image generation API using ComfyUI and SDXL Turbo on fal.
- [Deploy WAN LoRA Training](https://fal.ai/docs/examples/image-generation/deploy-wan-lora-training.md): Fine-tune WAN (text-to-video) with LoRA using your own short clips and images.
- [Deploy a Text-to-Video Model](https://fal.ai/docs/examples/video-generation/deploy-text-to-video-model.md): This example demonstrates how to build a sophisticated text-to-video generation service using Wan2.1, showcasing advanced techniques including custom safety checking with multiple AI models, prompt expansion using LLMs, video tensor processing, and comprehensive integration of multiple fal services…
- [Deploy 3D Progressive Rendering](https://fal.ai/docs/examples/video-generation/deploy-3d-progressive-rendering.md): Build a real-time text-to-3D and image-to-3D application with live voxel streaming using SAM-3D Objects.
- [Deploy Real-time Video-to-Video Model](https://fal.ai/docs/examples/video-generation/deploy-realtime-video-to-video-model.md): Run a real-time video-to-video pipeline that returns YOLO detections on your stream.
- [Deploy Real-time World Model](https://fal.ai/docs/examples/video-generation/deploy-realtime-world-model.md): Run a real-time world model demo powered by Matrix-Game.
- [Deploy Multi-GPU Inference](https://fal.ai/docs/examples/video-generation/deploy-multi-gpu-inference.md): Learn how to build a multi-GPU image generation service using data parallelism with Stable Diffusion XL, including real-time streaming and distributed worker coordination.
- [Generate video with WAN 2.2 across four GPUs](https://fal.ai/docs/examples/serverless/multi-gpu-video.md): Serve a text-to-video model too big for one GPU using fal.distributed and Ulysses sequence parallelism.
- [Deploy a Text-to-Speech Model](https://fal.ai/docs/examples/audio-speech/deploy-text-to-speech-model.md): This example demonstrates how to build a comprehensive text-to-speech service using Kokoro, showcasing CPU-efficient deployment, multi-language support, multiple endpoints with shared logic, and advanced audio processing techniques.
- [Deploy a Text-to-Music Model](https://fal.ai/docs/examples/audio-speech/deploy-text-to-music-model.md): This example demonstrates how to build a sophisticated text-to-music generation service using DiffRhythm, showcasing advanced fal features including custom Docker images, repository cloning, file downloading, and complex audio processing workflows.
- [Deploy Models with Custom Containers](https://fal.ai/docs/examples/deploy-models-with-custom-containers.md): fal now supports running apps within custom Docker containers, providing greater flexibility and control over your environment.
- [Migrate from Replicate](https://fal.ai/docs/documentation/development/migrate-from-replicate.md): A guide for migrating your Replicate Cog models to fal.
- [Migrate an External Docker Server](https://fal.ai/docs/documentation/development/migrate-external-docker-server.md): Deploy an existing Docker-based server (ComfyUI, custom APIs) to fal's serverless platform.
- [Migrate from Modal](https://fal.ai/docs/documentation/development/migrate-from-modal.md): A guide for migrating your Modal applications to fal.
- [Migrate from RunPod](https://fal.ai/docs/documentation/development/migrate-from-runpod.md): A guide for migrating your RunPod Serverless workers to fal.
- [Migrate from Baseten](https://fal.ai/docs/documentation/development/migrate-from-baseten.md): A guide for migrating your Baseten models and Chains to fal.
- [Cut cold start times with FlashPack and compiled caches](https://fal.ai/docs/examples/serverless/cut-cold-starts.md): Serve WAN 2.1 text-to-video with weights packed on /data, FlashPack disk-to-GPU loading, and a shared torch.compile kernel cache. Measured on real deploys: steady-state cold starts drop to roughly a third of the baseline.
- [Publish Custom Metrics with Prometheus Pushgateway](https://fal.ai/docs/examples/serverless/deploy-prometheus-pushgateway.md): Publish custom metrics on fal using Prometheus Pushgateway with direct port exposure and persistent storage.

- [Model API Reference (138 pages)](https://fal.ai/docs/_llms/model-api-reference.md): Documentation for Model API Reference.

## SDK Reference

- [Reference](https://fal.ai/docs/api-reference/index.md): Complete API and SDK reference documentation for fal

### Client Libraries

- [Client Libraries](https://fal.ai/docs/api-reference/client-libraries/index.md): Libraries for calling fal AI models from your applications
- [Swift Client](https://fal.ai/docs/api-reference/client-libraries/swift/index.md): fal client library for iOS, macOS, tvOS, and watchOS
- [Kotlin / Java Client](https://fal.ai/docs/api-reference/client-libraries/kotlin/index.md): fal client library for Android and JVM applications
- [Dart Client](https://fal.ai/docs/api-reference/client-libraries/dart/index.md): fal client library for Flutter applications

#### Python

- [Python Client](https://fal.ai/docs/api-reference/client-libraries/python/index.md): API reference for fal-client Python package
- [fal_client](https://fal.ai/docs/api-reference/client-libraries/python/fal_client.md): API reference for fal_client

#### JavaScript

- [JavaScript Client](https://fal.ai/docs/api-reference/client-libraries/javascript/index.md): API reference for @fal-ai/client
- [auth](https://fal.ai/docs/api-reference/client-libraries/javascript/auth.md): API reference for @fal-ai/client auth
- [client](https://fal.ai/docs/api-reference/client-libraries/javascript/client.md): API reference for @fal-ai/client client
- [config](https://fal.ai/docs/api-reference/client-libraries/javascript/config.md): API reference for @fal-ai/client config
- [middleware](https://fal.ai/docs/api-reference/client-libraries/javascript/middleware.md): API reference for @fal-ai/client middleware
- [queue](https://fal.ai/docs/api-reference/client-libraries/javascript/queue.md): API reference for @fal-ai/client queue
- [realtime](https://fal.ai/docs/api-reference/client-libraries/javascript/realtime.md): API reference for @fal-ai/client realtime
- [response](https://fal.ai/docs/api-reference/client-libraries/javascript/response.md): API reference for @fal-ai/client response
- [retry](https://fal.ai/docs/api-reference/client-libraries/javascript/retry.md): API reference for @fal-ai/client retry
- [storage](https://fal.ai/docs/api-reference/client-libraries/javascript/storage.md): API reference for @fal-ai/client storage
- [streaming](https://fal.ai/docs/api-reference/client-libraries/javascript/streaming.md): API reference for @fal-ai/client streaming
- [types.client](https://fal.ai/docs/api-reference/client-libraries/javascript/types.client.md): API reference for @fal-ai/client types.client
- [types.common](https://fal.ai/docs/api-reference/client-libraries/javascript/types.common.md): API reference for @fal-ai/client types.common
- [utils](https://fal.ai/docs/api-reference/client-libraries/javascript/utils.md): API reference for @fal-ai/client utils

### CLI Reference

- [CLI Reference](https://fal.ai/docs/api-reference/cli/index.md): Complete reference for the fal command-line interface
- [Installation](https://fal.ai/docs/api-reference/cli/installation.md)
- [fal auth](https://fal.ai/docs/api-reference/cli/auth.md)
- [fal deploy](https://fal.ai/docs/api-reference/cli/deploy.md)
- [fal environments](https://fal.ai/docs/api-reference/cli/environments.md)
- [fal files](https://fal.ai/docs/api-reference/cli/files.md)
- [fal run](https://fal.ai/docs/api-reference/cli/run.md)
- [fal queue](https://fal.ai/docs/api-reference/cli/queue.md): Manage application queues.
- [fal keys](https://fal.ai/docs/api-reference/cli/keys.md)
- [fal profile](https://fal.ai/docs/api-reference/cli/profile.md)
- [fal secrets](https://fal.ai/docs/api-reference/cli/secrets.md)
- [fal doctor](https://fal.ai/docs/api-reference/cli/doctor.md)
- [fal create](https://fal.ai/docs/api-reference/cli/create.md)
- [fal runners](https://fal.ai/docs/api-reference/cli/runners.md)
- [fal account](https://fal.ai/docs/api-reference/cli/teams.md)
- [fal api](https://fal.ai/docs/api-reference/cli/api.md)

#### fal apps

- [fal apps list](https://fal.ai/docs/api-reference/cli/apps/list.md)
- [fal apps list-rev](https://fal.ai/docs/api-reference/cli/apps/list-rev.md)
- [fal apps set-rev](https://fal.ai/docs/api-reference/cli/apps/set-rev.md)
- [fal apps rollout](https://fal.ai/docs/api-reference/cli/apps/rollout.md)
- [fal apps scale](https://fal.ai/docs/api-reference/cli/apps/scale.md)
- [fal apps runners](https://fal.ai/docs/api-reference/cli/apps/runners.md)
- [fal apps gpus](https://fal.ai/docs/api-reference/cli/apps/gpus.md)
- [fal apps delete](https://fal.ai/docs/api-reference/cli/apps/delete.md)
- [fal apps delete-rev](https://fal.ai/docs/api-reference/cli/apps/delete-rev.md)

### Python SDK

- [Python SDK](https://fal.ai/docs/api-reference/python-sdk/fal-app-reference.md): API reference for the fal Python package
- [pyproject.toml Reference](https://fal.ai/docs/api-reference/python-sdk/pyproject-toml.md): Configure fal Serverless apps in pyproject.toml for reusable app names, package entry points, runtime settings, scaling, and containers.
- [SyncServerlessClient](https://fal.ai/docs/api-reference/python-sdk/client.md): Synchronous Python client for fal Serverless. Manage apps, runners, and deployments programmatically.
- [fal.api](https://fal.ai/docs/api-reference/python-sdk/api-reference.md): API reference for fal.api
- [fal](https://fal.ai/docs/api-reference/python-sdk/fal.md): API reference for fal
- [fal.distributed](https://fal.ai/docs/api-reference/python-sdk/fal-distributed.md): API reference for fal.distributed
- [fal.exceptions](https://fal.ai/docs/api-reference/python-sdk/fal-exceptions.md): API reference for fal.exceptions
- [fal.toolkit](https://fal.ai/docs/api-reference/python-sdk/fal-toolkit.md): API reference for fal.toolkit
- [fal.toolkit.image.nsfw_filter](https://fal.ai/docs/api-reference/python-sdk/fal-toolkit-image-nsfw-filter.md): API reference for fal.toolkit.image.nsfw_filter

## Platform API

- [Introduction to Platform APIs](https://fal.ai/docs/api-reference/platform-apis/index.md): Platform APIs provide programmatic access to platform resources including model metadata, usage tracking, analytics, and fal Assets.
- [Authentication](https://fal.ai/docs/api-reference/platform-apis/authentication.md): Platform APIs require API keys for secure access to your user or team's data.
- [OpenAPI Schema](https://fal.ai/docs/api-reference/platform-apis/openapi-schema.md): The fal Platform API is documented using the OpenAPI 3.1 specification format.

### API Endpoints

- [Platform Metadata](https://fal.ai/docs/api-reference/platform-apis/meta.md): Returns platform metadata including webhook IP ranges for allowlisting.
- [Platform APIs for Models](https://fal.ai/docs/api-reference/platform-apis/for-models.md): Programmatic access to model metadata, pricing, usage tracking, and analytics
- [Model search](https://fal.ai/docs/platform-apis/v1/models.md): Unified endpoint for discovering model endpoints. Supports three usage modes:
- [Pricing](https://fal.ai/docs/platform-apis/v1/models/pricing.md): Returns 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. Values are expressed per model's billing unit in a given currency.
- [Estimate cost](https://fal.ai/docs/platform-apis/v1/models/pricing/estimate.md): Computes cost estimates using one of two methods:
- [Usage](https://fal.ai/docs/platform-apis/v1/models/usage.md): Returns paginated usage records for your workspace with filters for endpoint, user, date range, and auth method. Each item includes the billed unit quantity, the pre-discount unit price and cost_subtotal, any percentage discount applied, and the final cost_total (cost_subtotal − cost_discount).
- [Billing Events](https://fal.ai/docs/platform-apis/v1/models/billing-events.md): Returns paginated individual billing event records with filters for endpoint and date range. Each record includes the request ID, timestamp, endpoint, output units billed, and a cost breakdown in USD (cost_subtotal, cost_discount, cost_total; cost_estimate_nano_usd carries cost_total in nano USD).
- [Analytics](https://fal.ai/docs/platform-apis/v1/models/analytics.md): Time-bucketed metrics per model endpoint, including request counts, success/error rates, and latency percentiles. `prepare_duration` reflects queue/prepare time before execution; `duration` is request execution time. Use with the Queue/Webhooks flow to monitor SLAs.
- [List requests by endpoint(s)](https://fal.ai/docs/platform-apis/v1/models/requests/by-endpoint.md): Lists requests for one or more endpoints (same `endpoint_id` style as usage/explore: comma-separated or repeated query params, up to 50 IDs).
- [Delete request payloads](https://fal.ai/docs/platform-apis/v1/models/requests/payloads.md): Deletes the IO payloads and associated CDN output files for a specific request.
- [Platform APIs for Assets](https://fal.ai/docs/api-reference/platform-apis/for-assets.md): Programmatic access to fal Assets for browsing, searching, uploading, and organizing generated media
- [Browse assets](https://fal.ai/docs/platform-apis/v1/assets.md): Browse and semantically search fal Assets across all media, uploads, favorites, collections, tags, and character references.
- [Upload asset](https://fal.ai/docs/platform-apis/v1/assets/uploads.md): Upload asset for the authenticated user's fal Assets library.
- [Get asset](https://fal.ai/docs/platform-apis/v1/assets/get.md): Get an asset from the authenticated user's fal Assets library by asset ID; a vector ID is also accepted. Returns 404 when the asset has no live catalog record, including one whose deletion has not yet propagated to the search index.
- [Favorite asset](https://fal.ai/docs/platform-apis/v1/assets/favorite.md): Favorite an asset. Provide a request ID or vector ID; unresolved references are materialized before favorite state is added.
- [Unfavorite asset](https://fal.ai/docs/platform-apis/v1/assets/unfavorite.md): Unfavorite an asset by request ID or vector ID.
- [List asset collections](https://fal.ai/docs/platform-apis/v1/assets/collections.md): List asset collections for the authenticated user's fal Assets library.
- [Create asset collection](https://fal.ai/docs/platform-apis/v1/assets/collections/create.md): Create asset collection for the authenticated user's fal Assets library.
- [Get asset collection](https://fal.ai/docs/platform-apis/v1/assets/collections/get.md): Get asset collection for the authenticated user's fal Assets library.
- [Update asset collection](https://fal.ai/docs/platform-apis/v1/assets/collections/update.md): Update asset collection for the authenticated user's fal Assets library.
- [Delete asset collection](https://fal.ai/docs/platform-apis/v1/assets/collections/delete.md): Delete asset collection for the authenticated user's fal Assets library.
- [Favorite asset collection](https://fal.ai/docs/platform-apis/v1/assets/collections/favorite.md): Favorite an asset collection for the authenticated user's fal Assets library.
- [Unfavorite asset collection](https://fal.ai/docs/platform-apis/v1/assets/collections/unfavorite.md): Unfavorite an asset collection for the authenticated user's fal Assets library.
- [Browse assets in a collection](https://fal.ai/docs/platform-apis/v1/assets/collections/assets.md): Browse assets in a collection for the authenticated user's fal Assets library.
- [Add asset to collection](https://fal.ai/docs/platform-apis/v1/assets/collections/assets/add.md): Add 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. For character collections, this creates an explicit smart-entity link.
- [Remove asset from collection](https://fal.ai/docs/platform-apis/v1/assets/collections/assets/remove.md): Remove 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.
- [List asset characters](https://fal.ai/docs/platform-apis/v1/assets/characters.md): List asset characters for the authenticated user's fal Assets library.
- [Create asset character](https://fal.ai/docs/platform-apis/v1/assets/characters/create.md): Create an asset character for the authenticated user's fal Assets library. Prefer vector IDs or request IDs in reference_images for existing fal-generated assets; use fal-hosted image URLs only for standalone images. Unresolved ID references are materialized before character state is added.
- [Get asset character](https://fal.ai/docs/platform-apis/v1/assets/characters/get.md): Get asset character for the authenticated user's fal Assets library.
- [Update asset character](https://fal.ai/docs/platform-apis/v1/assets/characters/update.md): Update an asset character for the authenticated user's fal Assets library. Prefer vector IDs or request IDs in reference_images for existing fal-generated assets; use fal-hosted image URLs only for standalone images. Unresolved ID references are materialized before character state is added.
- [Delete asset character](https://fal.ai/docs/platform-apis/v1/assets/characters/delete.md): Delete asset character for the authenticated user's fal Assets library.
- [Favorite asset character](https://fal.ai/docs/platform-apis/v1/assets/characters/favorite.md): Favorite an asset character for the authenticated user's fal Assets library.
- [Unfavorite asset character](https://fal.ai/docs/platform-apis/v1/assets/characters/unfavorite.md): Unfavorite an asset character for the authenticated user's fal Assets library.
- [List asset tags](https://fal.ai/docs/platform-apis/v1/assets/tags.md): List asset tags for the authenticated user's fal Assets library.
- [Create asset tag](https://fal.ai/docs/platform-apis/v1/assets/tags/create.md): Create asset tag for the authenticated user's fal Assets library.
- [Set tags for an asset](https://fal.ai/docs/platform-apis/v1/assets/tags/set-for-asset.md): Set tags for an asset. Provide a request ID or vector ID; unresolved references are materialized before tag state is added.
- [Update asset tag](https://fal.ai/docs/platform-apis/v1/assets/tags/update.md): Update asset tag for the authenticated user's fal Assets library.
- [Delete asset tag](https://fal.ai/docs/platform-apis/v1/assets/tags/delete.md): Delete asset tag for the authenticated user's fal Assets library.
- [List tags for an asset](https://fal.ai/docs/platform-apis/v1/assets/tags/list-for-asset.md): List tags for an asset by asset ID; a vector ID is also accepted. Assets without a live catalog record return an empty tag list.
- [Assign tag to asset](https://fal.ai/docs/platform-apis/v1/assets/tags/assign.md): Assign a tag to an asset. Provide a request ID or vector ID; unresolved references are materialized before tag state is added.
- [Unassign tag from asset](https://fal.ai/docs/platform-apis/v1/assets/tags/unassign.md): Unassign a tag from an asset by request ID or vector ID.
- [Platform APIs for Storage](https://fal.ai/docs/api-reference/platform-apis/for-storage.md): Manage access control, signed URLs, and lifecycle settings for fal CDN files
- [Get file ACL](https://fal.ai/docs/platform-apis/v1/storage/files/acl/get.md): Returns the Access Control List currently applied to a fal CDN file.
- [Set file ACL](https://fal.ai/docs/platform-apis/v1/storage/files/acl/set.md): Replaces the Access Control List of a fal CDN file.
- [Sign file URL](https://fal.ai/docs/platform-apis/v1/storage/files/sign.md): Creates a signed URL that grants temporary access to a fal CDN file, regardless of its ACL. Useful for sharing access-restricted files.
- [Get storage settings](https://fal.ai/docs/platform-apis/v1/storage/settings/get.md): Returns the account-level storage lifecycle settings applied to newly uploaded fal CDN files:
- [Update storage settings](https://fal.ai/docs/platform-apis/v1/storage/settings/update.md): Replaces the account-level storage lifecycle settings applied to newly uploaded fal CDN files. Omitted or null fields are cleared (reset to the system default), so always send the full desired configuration. Sending an empty JSON object `{}` clears all settings. To change a single setting, first GET…
- [Platform APIs for Workflows](https://fal.ai/docs/api-reference/platform-apis/for-workflows.md): Programmatic access to workflow creation, metadata, listing, and details
- [List user workflows](https://fal.ai/docs/platform-apis/v1/workflows.md): List workflows for the authenticated user with optional search and filtering.
- [Create a workflow](https://fal.ai/docs/platform-apis/v1/workflows/create.md): Create a new workflow owned by the authenticated user.
- [Get workflow details](https://fal.ai/docs/platform-apis/v1/workflows/get.md): Get detailed information about a specific workflow, including its full contents/definition.
- [Platform APIs for Serverless](https://fal.ai/docs/api-reference/platform-apis/for-serverless.md): Programmatic access to serverless apps metadata, analytics, and billing
- [Queue Size](https://fal.ai/docs/platform-apis/v1/serverless/apps/queue.md): Retrieves the current queue size for a specific application.
- [Flush Application Queue](https://fal.ai/docs/platform-apis/v1/serverless/apps/flush-queue.md): Flushes all pending requests from an application's queue.
- [Application Revisions](https://fal.ai/docs/platform-apis/v1/serverless/apps/revisions.md): Returns the revision history for an application, newest first: every deployed version with its creation time, whether it is currently serving traffic, and a deployment status derived from recent deployment events.
- [Metrics](https://fal.ai/docs/platform-apis/v1/serverless/metrics.md): Returns Prometheus-compatible metrics in text format for integration into your observability stack
- [Analytics](https://fal.ai/docs/platform-apis/v1/serverless/analytics.md): Time-bucketed metrics for your serverless app endpoints, including request counts, success/error rates, and latency percentiles across all inbound traffic. `prepare_duration` reflects queue/prepare time before execution; `duration` is request execution time.
- [Usage](https://fal.ai/docs/platform-apis/v1/serverless/usage.md): Time-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. This matches the serverless portion of the dashboard usage view. Unlike `/v1/models/usage` (which reports mo…
- [List requests by endpoint(s)](https://fal.ai/docs/platform-apis/v1/serverless/requests/by-endpoint.md): Lists requests for one or more endpoints owned by the authenticated user. Use repeated or comma-separated `endpoint_id` (same as other platform list APIs).
- [List files (root)](https://fal.ai/docs/platform-apis/v1/serverless/files/list.md): Lists files and folders in the root of your project storage.
- [List files (directory)](https://fal.ai/docs/platform-apis/v1/serverless/files/list/directory.md): Lists files and folders within the specified directory path.
- [Download file](https://fal.ai/docs/platform-apis/v1/serverless/files/file/download.md): Downloads a file by its path. Proxies the underlying storage response.
- [Upload file from URL](https://fal.ai/docs/platform-apis/v1/serverless/files/file/upload-from-url.md): Creates a new file at the target path by downloading it from the provided URL.
- [Upload local file (multipart/form-data)](https://fal.ai/docs/platform-apis/v1/serverless/files/file/upload-local.md): Uploads a local file using multipart/form-data. The file field name must be `file_upload`.
- [Logs history (paginated)](https://fal.ai/docs/platform-apis/v1/serverless/logs/history.md): Returns paginated historical logs that match the provided filters.
- [Logs stream (SSE)](https://fal.ai/docs/platform-apis/v1/serverless/logs/stream.md): Streams live logs that match the provided filters using Server-Sent Events.
- [Platform APIs for Compute](https://fal.ai/docs/api-reference/platform-apis/for-compute.md): Programmatic access to compute instance management, lifecycle control, and monitoring
- [List Compute Instances](https://fal.ai/docs/platform-apis/v1/compute/instances/list.md): Returns a list of all compute instances belonging to the authenticated user's workspace.
- [Get Compute Instance](https://fal.ai/docs/platform-apis/v1/compute/instances/get.md): Retrieves detailed information about a specific compute instance by its ID.
- [Delete Compute Instance](https://fal.ai/docs/platform-apis/v1/compute/instances/delete.md): Deletes a specific compute instance by its ID. This action is irreversible.
- [Platform APIs for Keys](https://fal.ai/docs/api-reference/platform-apis/for-keys.md): Programmatic access to API key management, creation, and deletion
- [List API Keys](https://fal.ai/docs/platform-apis/v1/keys/list.md): Returns the API keys in the authenticated user's workspace that are on the `API` preset or the legacy `API` scope. Keys on other presets or custom policies are not listed.
- [Create API Key](https://fal.ai/docs/platform-apis/v1/keys/create.md): Creates a new API key on the `API` preset with the specified alias.
- [Delete API Key](https://fal.ai/docs/platform-apis/v1/keys/delete.md): Deletes an API key by its ID. This action is irreversible.
- [Platform APIs for Accounts](https://fal.ai/docs/api-reference/platform-apis/for-accounts.md): Programmatic access to account billing information, FOCUS-compliant cost reports, and model access controls
- [Account Billing](https://fal.ai/docs/platform-apis/v1/account/billing.md): Returns billing information for the authenticated account. Use the `expand` parameter to include additional details.
- [FOCUS Report](https://fal.ai/docs/platform-apis/v1/account/focus.md): Returns a FOCUS compliant billing report as a CSV download.
- [Model Access Controls Report](https://fal.ai/docs/platform-apis/v1/account/model-access-controls.md): Returns the current model access controls for your organization as a CSV download.
- [Platform APIs for Organizations](https://fal.ai/docs/api-reference/platform-apis/for-organization.md): Programmatic access to organization-wide team listings, cross-team usage records, FOCUS billing reports, and billing events
- [Organization Teams](https://fal.ai/docs/platform-apis/v1/organization/teams.md): Returns the list of teams in your organization with their details.
- [Organization Usage](https://fal.ai/docs/platform-apis/v1/organization/usage.md): Returns 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.
- [Organization FOCUS Report](https://fal.ai/docs/platform-apis/v1/organization/focus.md): Returns a FOCUS compliant billing report as a CSV download, spanning every team in your organization. Each invoiced billing customer is reported as a `BillingAccount`. Under shared (pooled) billing — one billing customer covering multiple teams — each row is additionally attributed to the calling te…
- [Organization Billing Events](https://fal.ai/docs/platform-apis/v1/organization/billing-events.md): Returns paginated individual billing event records across all teams in your organization, with each record attributed to a specific team via the `username` field. Each record includes a per-request cost breakdown in USD (cost_subtotal, cost_discount, cost_total; cost_estimate_nano_usd carries cost_t…

## Changelog

- [Product Changelog](https://fal.ai/docs/changelog.md): Latest features and updates to the fal platform

## OpenAPI Specs

- [v1](/docs/api-reference/platform-apis/openapi/v1.json)

## Optional

- [Status](https://status.fal.ai/)
- [Community](https://discord.gg/fal-ai)
- [Blog](https://blog.fal.ai/)

> The links below point to documentation indexes. Follow each `/_llms/` index recursively until you reach documentation pages.

## Indexes

- [Documentation (195 pages)](https://fal.ai/docs/_llms/documentation.md): Documentation for Documentation.
- [Model API Reference (138 pages)](https://fal.ai/docs/_llms/model-api-reference.md): Documentation for Model API Reference.