fal

aid: fal-ai
url: https://raw.githubusercontent.com/api-evangelist/fal-ai/refs/heads/main/apis.yml
apis:
  - aid: fal-ai:fal-model-apis
    name: fal Model APIs
    tags:
      - AI
      - Generative AI
      - Image Generation
      - Video Generation
      - Audio Generation
      - Multimodal
      - Inference
    humanURL: https://fal.ai/docs/model-apis/quickstart
    baseURL: https://queue.fal.run
    properties:
      - url: https://fal.ai/docs/model-apis/quickstart
        type: Documentation
      - url: https://fal.ai/models
        type: Documentation
        name: Model Gallery
      - url: openapi/fal-model-apis-openapi.yml
        type: OpenAPI
      - url: json-schema/fal-queue-request-schema.json
        type: JSONSchema
      - url: json-schema/fal-queue-status-schema.json
        type: JSONSchema
      - url: json-ld/fal-ai-context.jsonld
        type: JSONLD
    description: >-
      Unified queue-based REST API for invoking 1,000+ generative image, video, audio, and multimodal models hosted on
      fal's inference infrastructure. Submit a request to `https://queue.fal.run/{model-id}`, poll
      `/requests/{request_id}/status` or `/requests/{request_id}` for progress and results, or subscribe to webhook
      callbacks. Supports synchronous responses, asynchronous queueing, server-sent streaming progress, and request
      cancellation. Powers flagship models including FLUX, Veo 3, Kling 2.5, Wan 2.5, Seedream, Nano Banana, Qwen, SDXL,
      and Stable Diffusion variants.
  - aid: fal-ai:fal-realtime-api
    name: fal Realtime API
    tags:
      - AI
      - Generative AI
      - Realtime
      - WebSocket
      - Streaming
      - Inference
    humanURL: https://fal.ai/docs/model-apis/real-time
    baseURL: wss://realtime.fal.run
    properties:
      - url: https://fal.ai/docs/model-apis/real-time
        type: Documentation
      - url: https://github.com/fal-ai/real-time-demo-app
        type: CodeExamples
      - url: asyncapi/fal-ai-asyncapi.yml
        type: AsyncAPI
    description: >-
      WebSocket-based realtime inference for ultra-low latency interactive generative experiences such as LCM/SDXL
      sketch-to-image, live-portrait, and realtime upscaling. Bi-directional binary/JSON messaging keeps a persistent
      connection open so each frame, prompt, or pose adjustment is processed in milliseconds. Powers fal.realtime client
      utilities used in canvas apps, drawing tools, AR experiences, and live video pipelines.
  - aid: fal-ai:fal-streaming-api
    name: fal Streaming API
    tags:
      - AI
      - Generative AI
      - Streaming
      - Server-Sent Events
      - Inference
    humanURL: https://fal.ai/docs/model-apis/streaming
    baseURL: https://queue.fal.run
    properties:
      - url: https://fal.ai/docs/model-apis/streaming
        type: Documentation
      - url: asyncapi/fal-ai-asyncapi.yml
        type: AsyncAPI
    description: >-
      HTTP streaming endpoint (`/{model-id}/stream`) that emits progressive partial outputs as a model runs — used for
      LLM/VLM token streams, incremental video frames, and step-by-step image diffusion previews. Compatible with
      Server-Sent Events parsers in the official fal-client SDKs.
  - aid: fal-ai:fal-storage-api
    name: fal Storage API
    tags:
      - AI
      - Generative AI
      - File Upload
      - Storage
      - CDN
    humanURL: https://fal.ai/docs/model-apis/file-uploads
    baseURL: https://rest.alpha.fal.ai
    properties:
      - url: https://fal.ai/docs/model-apis/file-uploads
        type: Documentation
      - url: openapi/fal-storage-api-openapi.yml
        type: OpenAPI
    description: >-
      REST endpoints for uploading binary inputs (images, audio clips, reference frames, control maps) to fal's CDN so
      they can be referenced by URL when invoking model APIs. Issues short-lived signed upload URLs via
      `/storage/upload/initiate` and serves the resulting assets from `https://v3.fal.media`.
  - aid: fal-ai:fal-serverless-platform-api
    name: fal Serverless Platform API
    tags:
      - AI
      - Serverless
      - GPU
      - Deployments
      - Platform
    humanURL: https://fal.ai/docs/private-serverless-models
    baseURL: https://rest.alpha.fal.ai
    properties:
      - url: https://fal.ai/docs/private-serverless-models
        type: Documentation
      - url: https://github.com/fal-ai/fal
        type: SDK
        name: fal Python SDK and CLI
      - url: openapi/fal-serverless-platform-api-openapi.yml
        type: OpenAPI
    description: >-
      Programmatic management of custom fal Serverless applications — list, inspect, deploy, scale, and monitor
      user-defined GPU functions deployed with `@fal.function`, `fal.App`, or BYO containers. Covers app metadata,
      secrets, file volumes, scaling parameters (`keep_alive`, `min_concurrency`), and execution analytics.
  - aid: fal-ai:fal-models-catalog-api
    name: fal Models Catalog API
    tags:
      - AI
      - Generative AI
      - Catalog
      - Discovery
    humanURL: https://fal.ai/models
    baseURL: https://fal.ai
    properties:
      - url: https://fal.ai/models
        type: Documentation
    description: >-
      Read-only discovery endpoints for browsing fal's 1,000+ production model catalog, including model metadata,
      capability tags, pricing per output, supported parameters, example inputs, and OpenAPI schemas per model. Backs
      the model gallery, search, and SDK tooling.
  - aid: fal-ai:fal-compute-api
    name: fal Compute API
    tags:
      - AI
      - GPU
      - Compute
      - Infrastructure
      - Dedicated
    humanURL: https://fal.ai/compute
    baseURL: https://rest.alpha.fal.ai
    properties:
      - url: https://fal.ai/compute
        type: Documentation
    description: >-
      Provision and manage dedicated GPU instances (H100, H200, A100, B200) with full SSH access for training,
      fine-tuning, and persistent workloads. Hourly or per-second billing with no lock-in.
  - aid: fal-ai:fal-keys-api
    name: fal API Keys API
    tags:
      - AI
      - Administration
      - Authentication
      - API Keys
    humanURL: https://fal.ai/dashboard/keys
    baseURL: https://rest.alpha.fal.ai
    properties:
      - url: https://fal.ai/dashboard/keys
        type: Documentation
    description: >-
      Manage fal API keys — create, list, scope, and revoke keys used to authenticate against the Model, Storage,
      Serverless, and Compute APIs via the Authorization: Key $FAL_KEY header.
  - aid: fal-ai:fal-usage-billing-api
    name: fal Usage and Billing API
    tags:
      - AI
      - Administration
      - Usage
      - Billing
      - FinOps
    humanURL: https://fal.ai/dashboard/usage
    baseURL: https://rest.alpha.fal.ai
    properties:
      - url: https://fal.ai/dashboard/usage
        type: Documentation
    description: >-
      Programmatic access to usage metrics, per-model spend, GPU-second consumption, and invoicing history. Surfaces the
      same data shown on the fal dashboard so platform teams can pipe inference cost into internal FinOps tooling.
name: fal
tags:
  - AI
  - Artificial Intelligence
  - Generative AI
  - Generative Media
  - Image Generation
  - Video Generation
  - Audio Generation
  - Inference
  - Serverless
  - GPU
  - MCP
kind: contract
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
access: 3rd-Party
common:
  - type: PostmanWorkspace
    url: https://www.postman.com/kinlaneapi/fal/overview
  - type: ArazzoWorkflows
    url: arazzo/
    workflows:
      - url: arazzo/fal-ai-image-to-image-result-workflow.yml
        name: fal Upload, Run Image-To-Image With Webhook
        summary: Upload a reference image, submit an image-to-image job with a webhook, and confirm queue acceptance.
      - url: arazzo/fal-ai-queue-inference-workflow.yml
        name: fal Queue Inference
        summary: Submit a model inference job, poll the queue until it completes, then fetch the result.
      - url: arazzo/fal-ai-serverless-app-discovery-workflow.yml
        name: fal Serverless App Discovery
        summary: List deployed Serverless apps, then fetch full metadata and scaling for the first one.
      - url: arazzo/fal-ai-serverless-app-files-workflow.yml
        name: fal Serverless App Files Inspection
        summary: Confirm a Serverless app exists, then list files on its persistent /data volume.
      - url: arazzo/fal-ai-set-and-verify-secret-workflow.yml
        name: fal Set And Verify Serverless Secret
        summary: Create or replace a Serverless secret, then list secret names to confirm it is present.
      - url: arazzo/fal-ai-stream-inference-workflow.yml
        name: fal Streaming Inference
        summary: Run a model synchronously over the streaming endpoint to receive progressive output.
      - url: arazzo/fal-ai-submit-and-cancel-workflow.yml
        name: fal Submit And Conditionally Cancel
        summary: Submit an inference job, check its status once, and cancel it if it has not finished.
      - url: arazzo/fal-ai-upload-then-inference-workflow.yml
        name: fal Upload Asset Then Run Inference
        summary: Upload a binary reference asset to the fal CDN, then run an image-to-X model against it.
      - url: arazzo/fal-ai-webhook-submission-workflow.yml
        name: fal Webhook-Backed Submission
        summary: Submit an inference job with a webhook callback and confirm it was accepted into the queue.
  - type: Portal
    url: https://fal.ai
  - type: Documentation
    url: https://fal.ai/docs
  - type: Documentation
    name: Model APIs Quickstart
    url: https://fal.ai/docs/model-apis/quickstart
  - type: Documentation
    name: Model Gallery
    url: https://fal.ai/models
  - type: Documentation
    name: Authentication
    url: https://fal.ai/docs/authentication
  - type: Documentation
    name: Webhooks
    url: https://fal.ai/docs/model-apis/webhooks
  - type: Documentation
    name: Realtime
    url: https://fal.ai/docs/model-apis/real-time
  - type: Documentation
    name: Streaming
    url: https://fal.ai/docs/model-apis/streaming
  - type: Documentation
    name: File Uploads
    url: https://fal.ai/docs/model-apis/file-uploads
  - type: Documentation
    name: Private Serverless Models
    url: https://fal.ai/docs/private-serverless-models
  - type: GettingStarted
    url: https://fal.ai/docs/model-apis/quickstart
  - type: StatusPage
    url: https://status.fal.ai
  - type: Blog
    url: https://blog.fal.ai
  - type: SignUp
    url: https://fal.ai/login
  - type: Pricing
    url: https://fal.ai/pricing
  - type: Support
    name: Discord
    url: https://discord.gg/fal-ai
  - type: Forum
    url: https://discord.gg/fal-ai
  - type: TermsOfService
    url: https://fal.ai/legal/terms-of-service
  - type: PrivacyPolicy
    url: https://fal.ai/legal/privacy-policy
  - type: TrustCenter
    url: https://trust.fal.ai
  - type: LinkedIn
    url: https://www.linkedin.com/company/featuresandlabels
  - type: Twitter
    url: https://twitter.com/fal
  - type: GitHubOrganization
    url: https://github.com/fal-ai
  - type: SDK
    name: fal Python Client
    url: https://github.com/fal-ai/fal-client-python
  - type: SDK
    name: fal JavaScript Client
    url: https://github.com/fal-ai/fal-js
  - type: SDK
    name: fal Swift Client
    url: https://github.com/fal-ai/fal-swift
  - type: SDK
    name: fal Java/Kotlin Client
    url: https://github.com/fal-ai/fal-java
  - type: SDK
    name: fal Dart/Flutter Client
    url: https://github.com/fal-ai/fal-dart
  - type: SDK
    name: fal Python SDK / Serverless
    url: https://github.com/fal-ai/fal
  - type: Tool
    name: fal Terraform Provider
    url: https://github.com/fal-ai/terraform-provider-fal
  - type: Tool
    name: fal Blender Extension
    url: https://github.com/fal-ai/fal-blender-extension
  - type: Tool
    name: fal VS Code Extension (Serverless)
    url: https://github.com/fal-ai/serverless-vscode
  - type: CodeExamples
    name: Awesome fal
    url: https://github.com/fal-ai/awesome
  - type: CodeExamples
    name: Real-Time Demo App
    url: https://github.com/fal-ai/real-time-demo-app
  - type: CodeExamples
    name: fal Next.js Template
    url: https://github.com/fal-ai/fal-nextjs-template
  - type: Documentation
    name: MCP Server
    url: https://fal.ai/docs/mcp-server
  - type: Documentation
    name: ComfyUI Integration
    url: https://fal.ai/docs/comfyui
  - url: plans/fal-ai-plans-pricing.yml
    type: Plans
  - url: rate-limits/fal-ai-rate-limits.yml
    type: RateLimits
  - url: finops/fal-ai-finops.yml
    type: FinOps
  - type: Features
    data:
      - Unified queue-based REST API at https://queue.fal.run/{model-id} for 1,000+ generative models
      - >-
        Image generation models — FLUX (Schnell, Dev, Pro, Kontext Pro), Seedream V4, Nano Banana, Qwen, SDXL, SD3,
        Ideogram, Recraft
      - Video generation models — Veo 3, Kling 2.5 Turbo Pro, Wan 2.5, Seedance 2.0, Ovi, Hunyuan, Sora-class
      - Audio and voice models — Inworld TTS-1.5, ElevenLabs, MMAudio, MusicGen, Stable Audio
      - 3D and multimodal models — TripoSR, Hunyuan3D, LivePortrait, FaceChain
      - Synchronous, asynchronous queue, server-sent streaming, and WebSocket realtime invocation modes
      - Webhook callbacks for queue completion with HMAC signature verification
      - File uploads / CDN storage at https://v3.fal.media with signed upload URLs
      - >-
        fal Serverless — `@fal.function`, `fal.App`, BYO container deployment with autoscaling from 0 to thousands of
        GPUs
      - fal Compute — dedicated H100/H200/A100/B200 instances with SSH and per-second billing
      - Per-output billing (image, video second, audio minute) plus per-second GPU billing for custom deployments
      - 99.99% uptime SLA, SOC 2 compliance, private endpoints, and enterprise support
      - Proprietary Inference Engine — up to 10x faster than reference implementations
      - Official SDKs for Python (fal-client), JavaScript/TypeScript (@fal-ai/client), Swift, Java/Kotlin, Dart
      - fal CLI for serverless deploy / run / apps / secrets / auth
      - fal MCP Server exposing all 1,000+ models to AI assistants via the Model Context Protocol
      - ComfyUI and Blender extensions, plus Terraform provider for infra-as-code
      - Day-zero launch partner for major model releases (FLUX, Veo, Kling, Seedance, Wan, etc.)
    sources:
      - https://fal.ai
      - https://fal.ai/docs
      - https://fal.ai/pricing
      - https://fal.ai/models
      - https://github.com/fal-ai
      - https://blog.fal.ai
    updated: '2026-05-25'
created: '2026-05-25'
modified: '2026-05-25'
position: Consuming
description: >-
  fal (Features and Labels, Inc.) is a generative media platform providing the world's fastest API for running image,
  video, audio, and multimodal generative AI models. Through a unified queue-based REST API at https://queue.fal.run,
  plus realtime WebSocket and SSE streaming surfaces, fal serves 1,000+ production models — including FLUX, Veo 3,
  Kling, Wan, Seedream, Nano Banana, and Stable Diffusion — on autoscaling GPU infrastructure. fal Serverless lets
  developers ship custom models with `@fal.function` / `fal.App` / BYO containers, while fal Compute provides dedicated
  H100/H200/A100/B200 instances. Trusted by Canva, Perplexity, Poe, and 1.5M+ developers; Series D funded ($140M,
  Sequoia-led, December 2025); SOC 2 with 99.99% uptime.
maintainers:
  - FN: Kin Lane
    email: info@apievangelist.com
    X: apievangelist
    url: https://apievangelist.com
specificationVersion: '0.16'