fal
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.
Reference-quality API operations across every facet — a rich contract, published governance, transparent operations, and machine-readable commercial terms.
API Evangelist profiles fal the way a machine reads it — 66 machine-readable artifacts across 12 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — fal scores 75.5/100 (exemplar), with a separate agent-readiness read of 84/100 (agent native). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
How we profile fal
Each block below is one kind of artifact we hold for fal. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 12
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
fal Realtime API
WebSocket-based realtime inference for ultra-low latency interactive generative experiences such as LCM/SDXL sketch-to-image, live-portrait, and realtime upscaling. Bi-direction...
fal Streaming API
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-ste...
fal Models Catalog API
Read-only discovery endpoints for browsing fal's 1,000+ production model catalog, including model metadata, capability tags, pricing per output, supported parameters, example in...
fal Compute API
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...
fal API Keys API
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.
fal Usage and Billing API
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 pip...
fal Apps API
List and inspect deployed Serverless apps.
fal Files API
Manage files on persistent Serverless `/data` volumes.
fal Queue API
Submit, inspect, and cancel model inference jobs.
fal Secrets API
Manage per-org secrets injected into Serverless runs.
fal Storage API
Upload binary assets to the fal CDN.
fal Streaming API
Server-sent streaming of incremental model output.
Scroll within the panel for all 12 ·
Postman Collections 3
A runnable collection turns the contract into something a developer can execute in seconds. We profile them because the fastest way to trust an API is to make a real call against it.
Ready-to-run Postman collections for exercising this provider's APIs.
Open Collections 3
Open, tool-agnostic collections carry the same runnable value as Postman without locking you to one client — the portable, forkable form of the same exercise.
Open, tool-agnostic API collections (OpenAPI-derived and Bruno).
fal Model APIs
OPEN COLLECTIONfal Serverless Platform API
OPEN COLLECTIONfal Storage API
OPEN COLLECTIONArazzo Workflows 9
Real integrations are rarely a single call. Arazzo describes the multi-step sequences — auth, then create, then confirm — so both a human and an agent can follow the choreography, not just the endpoints.
Multi-step API workflows described with the Arazzo specification.
fal Upload, Run Image-To-Image With Webhook
Upload a reference image, submit an image-to-image job with a webhook, and confirm queue acceptance.
ARAZZOfal Queue Inference
Submit a model inference job, poll the queue until it completes, then fetch the result.
ARAZZOfal Serverless App Discovery
List deployed Serverless apps, then fetch full metadata and scaling for the first one.
ARAZZOfal Serverless App Files Inspection
Confirm a Serverless app exists, then list files on its persistent /data volume.
ARAZZOfal Set And Verify Serverless Secret
Create or replace a Serverless secret, then list secret names to confirm it is present.
ARAZZOfal Streaming Inference
Run a model synchronously over the streaming endpoint to receive progressive output.
ARAZZOfal Submit And Conditionally Cancel
Submit an inference job, check its status once, and cancel it if it has not finished.
ARAZZOfal Upload Asset Then Run Inference
Upload a binary reference asset to the fal CDN, then run an image-to-X model against it.
ARAZZOfal Webhook-Backed Submission
Submit an inference job with a webhook callback and confirm it was accepted into the queue.
ARAZZOScroll within the panel for all 9 ·
MCP Servers 1
Model Context Protocol servers expose these APIs directly to AI agents. We profile them because agent-native access is the fastest-growing way this provider's capabilities actually get used.
Model Context Protocol servers that expose these APIs to AI agents.
fal-ai-mcp.yml
MCP SERVERGraphQL 1
Where a provider ships GraphQL, the schema is the contract. We profile it alongside the REST surface so the whole interface is legible in one place.
GraphQL schemas published by this provider.
fal GraphQL API
fal is a fast serverless inference platform for AI models including image generation (Stable Diffusion, FLUX, Kling), video generation, speech, and custom models. The API covers...
GRAPHQLPricing Plans 1
Pricing is part of the interface. Machine-readable plans tell you what a tier costs and includes before you commit — one of the six things the Kin Score reads for commercial clarity.
Published pricing tiers and plan structures.
Fal Ai Plans Pricing
PLANSRate Limits 1
Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.
Documented rate limits and quota policies.
Fal Ai Rate Limits
RATE LIMITSFinOps 1
Cost, billing, and metering signals let a buyer model the financial operations of an API before it's live. We profile them for the same reason we profile pricing: the money is part of the contract.
Cost, billing, and metering signals for API financial operations.
Fal Ai Finops
FINOPSFeatures 18
The notable capabilities this provider advertises, captured as structured features so they can be searched and compared instead of read one landing page at a time.
Notable capabilities this provider offers.
Scroll within the panel for all 18 ·
Event Specifications 1
Not every API is request/response. AsyncAPI describes the event-driven and streaming side — the webhooks and channels — so the asynchronous half of the interface is documented the same way the synchronous half is.
AsyncAPI definitions for this provider's event-driven and streaming APIs.
fal Event-Driven APIs
AsyncAPI description of fal's event-driven inference surfaces. fal exposes two real-time channels in addition to its REST queue: (1) a Server-Sent Events stream that pushes incr...
ASYNCAPISemantic Vocabularies 1
JSON-LD contexts give the data shared meaning across APIs. We profile them because semantics are what let a machine reconcile 'customer' here with 'customer' somewhere else.
JSON-LD contexts and semantic vocabularies used across these APIs.
Fal Ai Context
JSON-LDSpectral Rules 3
Governance rulesets we run against this provider's specs — the automated checks behind parts of the score. Profiling them makes the quality bar explicit and re-runnable, not a matter of opinion.
JSON Schema 3
Standalone JSON Schema definitions describe the data models behind the API. We profile them so the shapes are validatable on their own — useful long after a single request is forgotten.
Standalone JSON Schema definitions for this provider's data models.
fal Image Model Result
JSON SCHEMAfal Queue Inference Request
JSON SCHEMAfal Queue Status Response
JSON SCHEMAJSON Structure 1
JSON Structure captures the data shapes in a form built for tooling — a complement to JSON Schema that keeps the model machine-legible.
JSON Structure definitions describing this provider's data shapes.
Fal Ai Structure
JSON STRUCTUREExamples 3
Real request and response payloads are what turn a spec from abstract into obvious — and they're one of the twelve things an agent needs to call an API correctly on the first try.
Example request and response payloads for these APIs.
Security Posture 3
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Resources
Every other property we hold for fal — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 3
Portal, sign-up, and the first successful call
Documentation 11
Reference material describing how the API behaves
Scroll within the panel for all 11 ·
Agent Surfaces 5
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 14
Pagination, idempotency, versioning, errors, and events
Scroll within the panel for all 14 ·
Build 16
SDKs, sample code, and the tooling you integrate with
Scroll within the panel for all 16 ·
Access & Security 4
Authentication, authorization, and security posture
Operate 5
Status, limits, changes, and where to get help
Commercial 5
Pricing, plans, and the legal terms of use
Company 3
The organization behind the API
← All providers · Data indexed from github.com/api-evangelist/fal-ai · machine-readable index on apis.io