makefx Models API
The model catalog and the inputs, references and prices it declares.
The model catalog and the inputs, references and prices it declares.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/makefx-app:makefx-app-models-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: makefx.app Models API
version: 0.0.0
description: 'Create images, video, and audio with your agent on one canvas. Pay per asset. Every result keeps its recipe.
Reads need an access token with the `read` scope, writes the `write` scope, and routes that manage the account itself accept only the browser session. Tokens come from the OAuth 2.1 authorization server described in `components.securitySchemes`; client registration is open and immediate.
Versioning is by date. The current version is 2026-09-10; send it as `API-Version` to pin a client, omit it for the current version. Every response under /api carries `API-Version` naming the version that answered; an unknown version is refused with 400 `unsupported_version`. A superseded version keeps answering for at least 90 days with `Deprecation` and `Sunset` headers (RFC 9745, RFC 8594) before it is removed.
Rate limits are per 60 seconds: 1200 requests per address for the API, with tighter buckets on the OAuth endpoints. Every response names the policy it passed under in `RateLimit-Policy`; a refusal is 429 with `Retry-After`.
Every error is the `ApiError` shape: an `error` code or sentence, and `error_description` when there is more to say. A request without a valid token answers 401 with a `WWW-Authenticate` header naming the protected resource metadata. Developer documentation: https://makefx.app/developers.'
contact:
name: Aleksei Krasnoperov
url: https://krasnoperov.me
servers:
- url: https://makefx.app
description: makefx.app
tags:
- name: Models
description: The model catalog and the inputs, references and prices it declares.
paths:
/api/models:
get:
operationId: modelsList
summary: List models
description: Lists the compact model catalog, optionally filtered by media kind, model family, or one model id, and scoped to an authorized space billing account. Speech voices are listed by GET /api/voices.
tags:
- Models
security:
- oauth2:
- read
- session: []
parameters:
- schema:
type: string
enum:
- image
- video
- audio
- 3d
required: false
name: kind
in: query
- schema:
type: string
enum:
- provider
- internal
- browser
required: false
name: family
in: query
- schema:
type: string
minLength: 1
description: Catalog id; returns only that model.
required: false
description: Catalog id; returns only that model.
name: model
in: query
- schema:
type: string
pattern: ^[a-z0-9]+(?:-[a-z0-9]+)*\/[a-z0-9]+(?:-[a-z0-9]+)*$
required: false
name: space_id
in: query
- $ref: '#/components/parameters/ApiVersion'
responses:
'200':
description: Success
content:
application/json:
schema:
type: object
properties:
credit_eur:
type: number
exclusiveMinimum: 0
models:
type: array
items:
type: object
properties:
id:
type: string
terms:
type: string
kind:
type: string
enum:
- image
- video
- audio
- 3d
family:
type: string
enum:
- provider
- internal
- browser
provider:
type: string
provider_model:
type: string
provider_model_kind:
type: string
enum:
- snapshot
- alias
label:
type: string
description:
type: string
default_for_kind:
type: boolean
availability:
type: string
enum:
- available
- preview
- unavailable
typical_seconds:
type: number
minimum: 0
params_schema:
type: object
additionalProperties: {}
reference_slots:
type: array
items:
type: object
properties:
slot:
type: string
kinds:
type: array
items:
type: string
enum:
- image
- video
- audio
- 3d
min:
type: integer
minimum: 0
max:
type: integer
minimum: 0
order:
type: string
exclusive_with:
type: array
items:
type: string
requires:
type: array
items:
type: string
required:
- slot
- kinds
- min
- max
output:
type: object
additionalProperties:
anyOf:
- type: string
- type: number
price:
type: object
properties:
unit:
type: string
enum:
- image
- second
- minute
- track
- asset
- none
credits:
type: number
minimum: 0
rules:
type: array
items:
type: object
properties:
when:
type: object
additionalProperties:
type: string
credits:
type: number
minimum: 0
required:
- when
- credits
minimum_credits:
type: number
minimum: 0
managed_markup_percent:
type: number
exclusiveMinimum: 0
description: Rates include this percentage markup. Before rounding per asset, use the larger of that markup or the own_key minimum fee added to the underlying reference charge.
own_key:
oneOf:
- type: object
properties:
unit:
type: string
enum:
- image
credits:
type: integer
exclusiveMinimum: 0
required:
- unit
- credits
- type: object
properties:
unit:
type: string
enum:
- second
credits:
type: integer
exclusiveMinimum: 0
seconds:
type: integer
exclusiveMinimum: 0
description: Duration of one started billing block, rounded per asset.
estimated_seconds:
type: number
exclusiveMinimum: 0
description: Quote duration when output length is not requested.
required:
- unit
- credits
- seconds
description: Independent platform fee when the paying account supplies the provider key.
until:
type:
- string
- 'null'
format: date-time
after:
type:
- object
- 'null'
properties:
credits:
type: number
minimum: 0
rules:
type: array
items:
type: object
properties:
when:
type: object
additionalProperties:
type: string
credits:
type: number
minimum: 0
required:
- when
- credits
required:
- credits
- rules
required:
- unit
- credits
- rules
- until
- after
error_codes:
type: array
items:
type: string
hidden:
type: boolean
renders_in:
type: string
enum:
- browser
prompt_max_chars:
type: integer
minimum: 0
description: Longest prompt accepted, in Unicode code points, where the model is stricter than the 8,000-character prompt cap; absent when only that cap applies.
required:
- id
- terms
- kind
- family
- provider
- provider_model
- provider_model_kind
- label
- description
- default_for_kind
- availability
- typical_seconds
- params_schema
- reference_slots
- output
- price
- error_codes
- hidden
actions:
type: array
items:
anyOf:
- type: object
properties:
id:
type: string
enum:
- describe
terms:
type: string
label:
type: string
tool:
type: string
enum:
- describe_asset
applies_to:
type: array
items:
type: string
enum:
- image
- video
- audio
- 3d
writes:
type: string
enum:
- traits
price:
type: object
properties:
unit:
type: string
enum:
- none
credits:
type: number
minimum: 0
required:
- unit
- credits
required:
- id
- terms
- label
- tool
- applies_to
- writes
- price
- type: object
properties:
id:
type: string
enum:
- align_audio
terms:
type: string
label:
type: string
tool:
type: string
enum:
- align_audio
applies_to:
type: array
prefixItems:
- type: string
enum:
- audio
writes:
type: string
enum:
- word_timings
price:
type: object
properties:
unit:
type: string
enum:
- minute
credits:
type: number
exclusiveMinimum: 0
minimum_credits:
type: integer
exclusiveMinimum: 0
required:
- unit
- credits
- minimum_credits
billing:
type: string
enum:
- platform
- own_key
required:
- id
- terms
- label
- tool
- applies_to
- writes
- price
required:
- credit_eur
- models
- actions
'400':
description: The request did not match the schema
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'401':
description: No valid credentials. WWW-Authenticate names the protected resource metadata to start from
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'403':
description: 'The credentials are valid but not enough: the token lacks the scope, or the action needs a browser session rather than an app token'
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'404':
description: Not found
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'429':
description: Rate limited. RateLimit names the policy; Retry-After says when to try again
headers:
Retry-After:
description: Seconds until the bucket refills
schema:
type: integer
RateLimit:
description: The policy, with nothing left in it
schema:
type: string
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'500':
description: Internal server error
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
/api/voices:
get:
operationId: voicesList
summary: List voices
description: Lists one page of the ElevenLabs voices that speech models accept as voice_id, from the platform library or, with space_id, the paying account library when it has its own key.
tags:
- Models
security:
- oauth2:
- read
- session: []
parameters:
- schema:
type: string
pattern: ^[a-z0-9]+(?:-[a-z0-9]+)*\/[a-z0-9]+(?:-[a-z0-9]+)*$
description: Selects the authorized Space whose account pays for speech; omit for the platform voices.
required: false
description: Selects the authorized Space whose account pays for speech; omit for the platform voices.
name: space_id
in: query
- schema:
type: string
minLength: 1
maxLength: 100
description: Case-insensitive text matched against voice names, descriptions, and labels.
required: false
description: Case-insensitive text matched against voice names, descriptions, and labels.
name: query
in: query
- schema:
type: integer
minimum: 1
maximum: 50
default: 25
required: false
name: limit
in: query
- schema:
type: string
pattern: ^[1-9]\d{0,5}$
description: next_cursor from the previous page.
required: false
description: next_cursor from the previous page.
name: cursor
in: query
- $ref: '#/components/parameters/ApiVersion'
responses:
'200':
description: Success
content:
application/json:
schema:
type: object
properties:
voices:
type: array
items:
type: object
properties:
voice_id:
type: string
name:
type: string
description:
type: string
preview_url:
type: string
required:
- voice_id
- name
default_voice_id:
type:
- string
- 'null'
description: The voice speech uses when voice_id is omitted; null when voice_id is required.
next_cursor:
type:
- string
- 'null'
required:
- voices
- default_voice_id
- next_cursor
'400':
description: The request did not match the schema
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'401':
description: No valid credentials. WWW-Authenticate names the protected resource metadata to start from
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'403':
description: 'The credentials are valid but not enough: the token lacks the scope, or the action needs a browser session rather than an app token'
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'404':
description: Not found
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'429':
description: Rate limited. RateLimit names the policy; Retry-After says when to try again
headers:
Retry-After:
description: Seconds until the bucket refills
schema:
type: integer
RateLimit:
description: The policy, with nothing left in it
schema:
type: string
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'500':
description: Internal server error
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
components:
parameters:
ApiVersion:
name: API-Version
in: header
required: false
description: The API version the client was written against. Omit it for the current version, 2026-09-10. The response carries the same header, naming the version that answered.
schema:
type: string
enum:
- '2026-09-10'
schemas:
ApiError:
type: object
properties:
error:
type: string
description: A short code or sentence naming what went wrong
error_description:
type: string
description: More for a person, when the code alone would not do
retryable:
type: boolean
description: Whether repeating the same request may succeed
details:
type: object
additionalProperties: {}
description: Machine-readable error context
required:
- error
securitySchemes:
oauth2:
type: oauth2
description: 'OAuth 2.1 authorization code with PKCE (S256), issued by this deployment. Register a client at the registration endpoint or present a Client ID Metadata Document, then send the person to authorize. Metadata: /.well-known/oauth-authorization-server.'
flows:
authorizationCode:
authorizationUrl: https://makefx.app/api/oauth/authorize
tokenUrl: https://makefx.app/api/oauth/token
refreshUrl: https://makefx.app/api/oauth/token
scopes:
openid: Confirm who you are
profile: See your name
email: See your email address
read: Read your data
write: Change your data on your behalf
session:
type: apiKey
in: cookie
name: auth_token
description: The browser session set by signing in with Google. Routes that manage the account itself accept only this, never an app token.
registrationToken:
type: http
scheme: bearer
description: The registration access token returned by client registration (RFC 7592). It manages that one registration and nothing else.
externalDocs:
url: https://makefx.app/developers
description: Developer portal