fal · Capability

fal Model APIs — Queue

fal Model APIs — Queue. 4 operations (submit, status, result, cancel) for invoking 1,000+ generative models through the unified https://queue.fal.run REST surface. Self-contained Naftiko capability covering one fal business surface.

fal Model APIs — Queue is a Naftiko capability published by fal, one of 7 capabilities the APIs.io network indexes for this provider. It bundles 4 operations across the GET, POST, and PUT methods rooted at /v1/models/{…}/{…}/requests.

The capability includes 2 read-only operations and 2 state-changing operations. Lead operation: Submit a generative model inference job to fal. Can be deployed as a REST endpoint, MCP tool, or Agent Skill via Naftiko.

Tagged areas include Fal, Generative AI, Queue, and Inference.

Run with Naftiko FalGenerative AIQueueInference

What You Can Do

POST
Submitrequest — Submit a new inference job.
/v1/models/{model_owner}/{model_name}/requests
GET
Getstatus — Get inference job status.
/v1/models/{model_owner}/{model_name}/requests/{request_id}/status
GET
Getresult — Get inference job result.
/v1/models/{model_owner}/{model_name}/requests/{request_id}
PUT
Cancel — Cancel an inference job.
/v1/models/{model_owner}/{model_name}/requests/{request_id}/cancel

MCP Tools

fal-submit-request

Submit a generative model inference job to fal.

fal-get-status

Get the current status of a fal inference job.

read-only idempotent
fal-get-result

Retrieve the final output of a completed fal inference job.

read-only idempotent
fal-cancel-request

Cancel an in-queue or in-progress fal inference job.

idempotent

Capability Spec

model-apis-queue.yaml Raw ↑ 
naftiko: 1.0.0-alpha2
info:
  label: fal Model APIs — Queue
  description: 'fal Model APIs — Queue. 4 operations (submit, status, result, cancel) for invoking 1,000+ generative
    models through the unified https://queue.fal.run REST surface. Self-contained Naftiko capability covering
    one fal business surface.'
  tags:
  - Fal
  - Generative AI
  - Queue
  - Inference
  created: '2026-05-25'
  modified: '2026-05-25'
binds:
- namespace: env
  keys:
    FAL_KEY: FAL_KEY
capability:
  consumes:
  - type: http
    namespace: model-apis-queue
    baseUri: https://queue.fal.run
    description: fal Model APIs — Queue business capability. Self-contained, no shared references.
    resources:
    - name: model-invocation
      path: /{model_owner}/{model_name}
      operations:
      - name: submitrequest
        method: POST
        description: Submit a new inference job and receive a request_id.
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: model_owner
          in: path
          type: string
          required: true
        - name: model_name
          in: path
          type: string
          required: true
        - name: body
          in: body
          type: object
          description: Model-specific JSON input.
          required: true
    - name: request-status
      path: /{model_owner}/{model_name}/requests/{request_id}/status
      operations:
      - name: getstatus
        method: GET
        description: Get current status (IN_QUEUE, IN_PROGRESS, COMPLETED, FAILED, CANCELED).
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: model_owner
          in: path
          type: string
          required: true
        - name: model_name
          in: path
          type: string
          required: true
        - name: request_id
          in: path
          type: string
          required: true
    - name: request-result
      path: /{model_owner}/{model_name}/requests/{request_id}
      operations:
      - name: getresult
        method: GET
        description: Retrieve the final inference output once the request has completed.
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: model_owner
          in: path
          type: string
          required: true
        - name: model_name
          in: path
          type: string
          required: true
        - name: request_id
          in: path
          type: string
          required: true
    - name: request-cancel
      path: /{model_owner}/{model_name}/requests/{request_id}/cancel
      operations:
      - name: cancel
        method: PUT
        description: Cancel an in-queue or in-progress request.
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: model_owner
          in: path
          type: string
          required: true
        - name: model_name
          in: path
          type: string
          required: true
        - name: request_id
          in: path
          type: string
          required: true
    authentication:
      type: apikey
      key: Authorization
      value: 'Key {{env.FAL_KEY}}'
      placement: header
  exposes:
  - type: rest
    namespace: model-apis-queue-rest
    port: 8080
    description: REST adapter for fal Model APIs — Queue. One Spectral-compliant resource per consumed operation,
      prefixed with /v1.
    resources:
    - path: /v1/models/{model_owner}/{model_name}/requests
      name: model-invocation
      description: REST surface for submitting model inference jobs.
      operations:
      - method: POST
        name: submitrequest
        description: Submit a new inference job.
        call: model-apis-queue.submitrequest
        with:
          model_owner: rest.path.model_owner
          model_name: rest.path.model_name
          body: rest.body
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/models/{model_owner}/{model_name}/requests/{request_id}/status
      name: request-status
      description: REST surface for fetching job status.
      operations:
      - method: GET
        name: getstatus
        description: Get inference job status.
        call: model-apis-queue.getstatus
        with:
          model_owner: rest.path.model_owner
          model_name: rest.path.model_name
          request_id: rest.path.request_id
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/models/{model_owner}/{model_name}/requests/{request_id}
      name: request-result
      description: REST surface for fetching final result.
      operations:
      - method: GET
        name: getresult
        description: Get inference job result.
        call: model-apis-queue.getresult
        with:
          model_owner: rest.path.model_owner
          model_name: rest.path.model_name
          request_id: rest.path.request_id
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/models/{model_owner}/{model_name}/requests/{request_id}/cancel
      name: request-cancel
      description: REST surface for canceling jobs.
      operations:
      - method: PUT
        name: cancel
        description: Cancel an inference job.
        call: model-apis-queue.cancel
        with:
          model_owner: rest.path.model_owner
          model_name: rest.path.model_name
          request_id: rest.path.request_id
        outputParameters:
        - type: object
          mapping: $.
  - type: mcp
    namespace: model-apis-queue-mcp
    port: 9090
    transport: http
    description: MCP adapter for fal Model APIs — Queue. One tool per consumed operation, routed inline through
      this capability's consumes block.
    tools:
    - name: fal-submit-request
      description: Submit a generative model inference job to fal.
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: model-apis-queue.submitrequest
      with:
        model_owner: tools.model_owner
        model_name: tools.model_name
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.
    - name: fal-get-status
      description: Get the current status of a fal inference job.
      hints:
        readOnly: true
        destructive: false
        idempotent: true
      call: model-apis-queue.getstatus
      with:
        model_owner: tools.model_owner
        model_name: tools.model_name
        request_id: tools.request_id
      outputParameters:
      - type: object
        mapping: $.
    - name: fal-get-result
      description: Retrieve the final output of a completed fal inference job.
      hints:
        readOnly: true
        destructive: false
        idempotent: true
      call: model-apis-queue.getresult
      with:
        model_owner: tools.model_owner
        model_name: tools.model_name
        request_id: tools.request_id
      outputParameters:
      - type: object
        mapping: $.
    - name: fal-cancel-request
      description: Cancel an in-queue or in-progress fal inference job.
      hints:
        readOnly: false
        destructive: true
        idempotent: true
      call: model-apis-queue.cancel
      with:
        model_owner: tools.model_owner
        model_name: tools.model_name
        request_id: tools.request_id
      outputParameters:
      - type: object
        mapping: $.