The minimax-h3 API from CraftStory — 7 operation(s) for minimax-h3.
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/craftstory-com:craftstory-com-minimax-h3-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. 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: Craftstory Com Minimax H3 API
version: 1.0.0
description: 'Operations tagged minimax-h3 across 2 of this provider''s published API definitions: craftstory-com-swagger.json, craftstory-com-openapi.yml. Each path carries the servers of the definition it was published in.'
servers:
- url: https://api.craftstory.com/api/v1
security:
- ApiKey: []
tags:
- name: minimax-h3
paths:
/minimax-h3/:
parameters: []
get:
operationId: minimax-h3_list
summary: MiniMax H3 — one photo in, a short video out (up to 15 s)
description: 'Accepts ``Authorization: Bearer sk-cs-...`` API keys. Create a job with
``POST``, poll ``GET /minimax-h3/{id}/status/`` until ``done``, then read
``video_url`` from ``GET /minimax-h3/{id}/``.'
parameters:
- name: limit
in: query
description: Number of results to return per page.
required: false
schema:
type: integer
- name: offset
in: query
description: The initial index from which to return the results.
required: false
schema:
type: integer
responses:
'200':
description: ''
content:
application/json:
schema:
required:
- count
- results
type: object
properties:
count:
type: integer
next:
type:
- string
- 'null'
format: uri
previous:
type:
- string
- 'null'
format: uri
results:
type: array
items:
$ref: '#/components/schemas/MiniMaxH3'
tags:
- minimax-h3
post:
operationId: minimax-h3_create
summary: 'Basic mode: image + scene description + duration'
description: 'No audio: the model animates the photo from `user_prompt` and generates the soundtrack itself. `requested_duration_s` (5–15) sets the length and the price. Extra references belong to the audio-driven endpoint.
Poll `GET /minimax-h3/{id}/status/`, then read `video_url` from `GET /minimax-h3/{id}/`.'
responses:
'201':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/MiniMaxH3'
tags:
- minimax-h3
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/MiniMaxH3BasicCreate'
required: true
servers:
- url: https://api.craftstory.com/api/v1
/minimax-h3/avatar/:
parameters: []
post:
operationId: minimax-h3_create_avatar
summary: 'Avatar mode: your custom avatar speaks your text in its own voice'
description: '`avatar_id` is a custom avatar from `GET /api/v1/image2video/avatars/` whose `models` include `minimax-h3` (sample actors are not accepted). `speech_text` is spoken verbatim; `user_prompt` describes the scene and manner; `scene_id` picks one of the avatar''s scenes (default: the first). 5–14 s: `requested_duration_s` or, when omitted, the length that fits the text. Up to 3 extra references (images or audio, no video) as repeated multipart `reference_files` with `reference_captions`; the clip ceiling drops with extra photos (0–1: 14 s, 2: 12 s, 3: 10 s). The first run of an avatar builds its profile (about a minute more); later runs reuse it. 5.6 credits per second.
Poll `GET /minimax-h3/{id}/status/`, then read `video_url` from `GET /minimax-h3/{id}/`.'
responses:
'201':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/MiniMaxH3'
tags:
- minimax-h3
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/MiniMaxH3AvatarCreate'
required: true
servers:
- url: https://api.craftstory.com/api/v1
/minimax-h3/reference/:
parameters: []
post:
operationId: minimax-h3_create_reference
summary: 'Reference mode: image + audio or description (+ extra references)'
description: 'With one `audios` id the clip is lip-synced to it (the first 15 s are rendered and billed) and `user_prompt` is optional. Without audio, `requested_duration_s` (5–15) and `user_prompt` are required: the model voices the lines written in quotes in the description and generates the soundtrack. Up to 8 image / 3 video / 2 audio extra references go in repeated multipart `reference_files` entries with matching `reference_captions`.
Poll `GET /minimax-h3/{id}/status/`, then read `video_url` from `GET /minimax-h3/{id}/`.'
responses:
'201':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/MiniMaxH3'
tags:
- minimax-h3
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/MiniMaxH3ReferenceCreate'
required: true
servers:
- url: https://api.craftstory.com/api/v1
/minimax-h3/{id}/:
parameters:
- name: id
in: path
required: true
schema:
type: string
get:
operationId: minimax-h3_read
summary: MiniMax H3 — one photo in, a short video out (up to 15 s)
description: 'Accepts ``Authorization: Bearer sk-cs-...`` API keys. Create a job with
``POST``, poll ``GET /minimax-h3/{id}/status/`` until ``done``, then read
``video_url`` from ``GET /minimax-h3/{id}/``.'
responses:
'200':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/MiniMaxH3'
tags:
- minimax-h3
delete:
operationId: minimax-h3_delete
summary: MiniMax H3 — one photo in, a short video out (up to 15 s)
description: 'Accepts ``Authorization: Bearer sk-cs-...`` API keys. Create a job with
``POST``, poll ``GET /minimax-h3/{id}/status/`` until ``done``, then read
``video_url`` from ``GET /minimax-h3/{id}/``.'
responses:
'204':
description: ''
tags:
- minimax-h3
servers:
- url: https://api.craftstory.com/api/v1
/minimax-h3/{id}/asset/:
parameters:
- name: id
in: path
required: true
schema:
type: string
post:
operationId: minimax-h3_create_asset
description: 'Add a finished MiniMax video to the media assets library —
mirror of the i2v/v2v asset actions.'
responses:
'201':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/MiniMaxH3'
tags:
- minimax-h3
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/MiniMaxH3'
required: true
summary: Minimax h3 create asset
x-summary-source: derived
servers:
- url: https://api.craftstory.com/api/v1
/minimax-h3/{id}/status/:
parameters:
- name: id
in: path
required: true
schema:
type: string
get:
operationId: minimax-h3_get_status
description: 'Lightweight polling endpoint — the same shape as
``/image2video/{id}/status/`` so integrations can share one loop.'
responses:
'200':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/MiniMaxH3Status'
tags:
- minimax-h3
summary: Minimax h3 get status
x-summary-source: derived
servers:
- url: https://api.craftstory.com/api/v1
/minimax-h3/{id}/upscale/:
parameters:
- name: id
in: path
required: true
schema:
type: string
post:
operationId: minimax-h3_make_upscale
description: 'Upscale a finished MiniMax video x2 (e.g. 1344x768 -> 2688x1536) as a
NEW record, mirroring i2v: the original stays, the clone carries the
upscaled result. Priced at the flat upscale rate (0.2/s).'
responses:
'201':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/MiniMaxH3'
tags:
- minimax-h3
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/MiniMaxH3'
required: true
summary: Minimax h3 make upscale
x-summary-source: derived
servers:
- url: https://api.craftstory.com/api/v1
components:
schemas:
MiniMaxH3Status:
type: object
properties:
status:
title: Status
type: string
enum:
- created
- in_progress_moderation
- rejected_image
- rejected_text
- rejected_reference
- in_progress_prompt
- in_progress_video_queued
- in_progress_video_generating
- done
- failed
status_failed:
title: Status failed
type:
- string
- 'null'
enum:
- failed_image_moderation
- rejected_image
- rejected_text
- rejected_reference
- failed_prompt
- failed_generation
- null
status_percentage:
title: Status percentage
type: integer
maximum: 32767
minimum: 0
credits_refunded:
title: Credits refunded
type: string
readOnly: true
MiniMaxH3:
required:
- credits
type: object
properties:
id:
title: Id
type: string
format: uuid
readOnly: true
name:
title: Name
type:
- string
- 'null'
maxLength: 512
status:
title: Status
type: string
enum:
- created
- in_progress_moderation
- rejected_image
- rejected_text
- rejected_reference
- in_progress_prompt
- in_progress_video_queued
- in_progress_video_generating
- done
- failed
status_failed:
title: Status failed
type:
- string
- 'null'
enum:
- failed_image_moderation
- rejected_image
- rejected_text
- rejected_reference
- failed_prompt
- failed_generation
- null
status_percentage:
title: Status percentage
type: integer
maximum: 32767
minimum: 0
credits_refunded:
title: Credits refunded
type: string
readOnly: true
image:
title: Image
type: string
readOnly: true
format: uri
image_1000:
title: Image 1000
type:
- string
- 'null'
readOnly: true
video_first_frame_1000:
title: Video first frame 1000
type:
- string
- 'null'
readOnly: true
user_prompt:
title: User scene description
type: string
credits:
title: Credits
type: integer
maximum: 2147483647
minimum: 0
video_url:
title: Video url
type:
- string
- 'null'
readOnly: true
audios:
type: array
items:
type: string
format: uuid
readOnly: true
uniqueItems: true
references:
type: array
items:
type: object
readOnly: true
requested_duration_s:
title: Requested duration, seconds
type:
- integer
- 'null'
maximum: 32767
minimum: 0
mode:
title: Mode
type: string
readOnly: true
is_upscale:
title: Is upscale
type: boolean
readOnly: true
billable_duration_s:
title: Billable duration s
type: integer
readOnly: true
asset:
title: Asset
type:
- string
- 'null'
format: uuid
created:
title: Created
type: string
format: date-time
readOnly: true
updated:
title: Updated
type: string
format: date-time
readOnly: true
avatar_id:
title: Avatar id
type: string
readOnly: true
scene_id:
title: Scene id
type: string
readOnly: true
speech_text:
title: Spoken lines (avatar mode)
type: string
aspect_ratio:
title: Aspect ratio
type: string
readOnly: true
MiniMaxH3AvatarCreate:
required:
- avatar_id
- speech_text
type: object
properties:
id:
title: Id
type: string
format: uuid
readOnly: true
name:
title: Name
type:
- string
- 'null'
maxLength: 512
avatar_id:
title: Avatar id
description: A custom avatar id from GET /api/v1/image2video/avatars/ (models includes minimax-h3).
type: string
format: uuid
scene_id:
title: Scene id
description: 'One of the avatar''s scenes (GET /image2video/avatars/{id}/scenes/); default: the first one.'
type: string
format: uuid
speech_text:
title: Speech text
description: What the avatar says, verbatim (about 15 characters per second).
type: string
maxLength: 2000
minLength: 1
user_prompt:
title: User prompt
description: Scene and manner, e.g. 'Selfie video, shows the product'.
type: string
default: Talking to the camera.
requested_duration_s:
title: Requested duration s
description: '5-14 s; default: derived from speech_text.'
type: integer
maximum: 14
minimum: 5
aspect_ratio:
title: Aspect ratio
description: 'Output shape: auto (nearest native ratio to the photo), 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21, or 4:5 (rendered as 3:4 and center-cropped).'
type: string
enum:
- auto
- '21:9'
- '16:9'
- '4:3'
- '1:1'
- '3:4'
- '9:16'
- '9:21'
- '4:5'
default: auto
credits:
title: Credits
type: integer
readOnly: true
MiniMaxH3ReferenceCreate:
type: object
properties:
id:
title: Id
type: string
format: uuid
readOnly: true
name:
title: Name
type:
- string
- 'null'
maxLength: 512
image:
title: Image
type: string
readOnly: true
format: uri
audios:
type: array
items:
type: string
format: uuid
uniqueItems: true
user_prompt:
title: User scene description
type: string
requested_duration_s:
title: Requested duration s
type: integer
maximum: 15
minimum: 5
aspect_ratio:
title: Aspect ratio
description: 'Output shape: auto (nearest native ratio to the photo), 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21, or 4:5 (rendered as 3:4 and center-cropped).'
type: string
enum:
- auto
- '21:9'
- '16:9'
- '4:3'
- '1:1'
- '3:4'
- '9:16'
- '9:21'
- '4:5'
default: auto
credits:
title: Credits
type: integer
readOnly: true
MiniMaxH3BasicCreate:
required:
- user_prompt
- requested_duration_s
type: object
properties:
id:
title: Id
type: string
format: uuid
readOnly: true
name:
title: Name
type:
- string
- 'null'
maxLength: 512
image:
title: Image
type: string
readOnly: true
format: uri
user_prompt:
title: User prompt
type: string
minLength: 1
requested_duration_s:
title: Requested duration s
type: integer
maximum: 15
minimum: 5
aspect_ratio:
title: Aspect ratio
description: 'Output shape: auto (nearest native ratio to the photo), 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21, or 4:5 (rendered as 3:4 and center-cropped).'
type: string
enum:
- auto
- '21:9'
- '16:9'
- '4:3'
- '1:1'
- '3:4'
- '9:16'
- '9:21'
- '4:5'
default: auto
credits:
title: Credits
type: integer
readOnly: true
MiniMaxH3AvatarCreate_2:
required:
- avatar_id
- speech_text
type: object
properties:
id:
title: Id
type: string
format: uuid
readOnly: true
name:
title: Name
type:
- string
- 'null'
maxLength: 512
avatar_id:
title: Avatar id
description: A custom avatar id from GET /api/v1/image2video/avatars/ (models includes minimax-h3).
type: string
format: uuid
scene_id:
title: Scene id
description: 'One of the avatar''s scenes (GET /image2video/avatars/{id}/scenes/); default: the first one.'
type: string
format: uuid
speech_text:
title: Speech text
description: What the avatar says, verbatim (about 15 characters per second).
type: string
maxLength: 2000
minLength: 1
user_prompt:
title: User prompt
description: Scene and manner, e.g. 'Selfie video, shows the product'.
type: string
default: Talking to the camera.
requested_duration_s:
title: Requested duration s
description: '5-14 s; default: derived from speech_text.'
type: integer
maximum: 14
minimum: 5
aspect_ratio:
title: Aspect ratio
description: 'Output shape: auto (nearest native ratio to the photo), 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21, or 4:5 (rendered as 3:4 and center-cropped).'
type: string
enum:
- auto
- 1269
- 969
- 243
- 61
- 184
- 556
- 561
- 245
default: auto
credits:
title: Credits
type: integer
readOnly: true
MiniMaxH3ReferenceCreate_2:
type: object
properties:
id:
title: Id
type: string
format: uuid
readOnly: true
name:
title: Name
type:
- string
- 'null'
maxLength: 512
image:
title: Image
type: string
readOnly: true
format: uri
audios:
type: array
items:
type: string
format: uuid
uniqueItems: true
user_prompt:
title: User scene description
type: string
requested_duration_s:
title: Requested duration s
type: integer
maximum: 15
minimum: 5
aspect_ratio:
title: Aspect ratio
description: 'Output shape: auto (nearest native ratio to the photo), 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21, or 4:5 (rendered as 3:4 and center-cropped).'
type: string
enum:
- auto
- 1269
- 969
- 243
- 61
- 184
- 556
- 561
- 245
default: auto
credits:
title: Credits
type: integer
readOnly: true
MiniMaxH3BasicCreate_2:
required:
- user_prompt
- requested_duration_s
type: object
properties:
id:
title: Id
type: string
format: uuid
readOnly: true
name:
title: Name
type:
- string
- 'null'
maxLength: 512
image:
title: Image
type: string
readOnly: true
format: uri
user_prompt:
title: User prompt
type: string
minLength: 1
requested_duration_s:
title: Requested duration s
type: integer
maximum: 15
minimum: 5
aspect_ratio:
title: Aspect ratio
description: 'Output shape: auto (nearest native ratio to the photo), 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21, or 4:5 (rendered as 3:4 and center-cropped).'
type: string
enum:
- auto
- 1269
- 969
- 243
- 61
- 184
- 556
- 561
- 245
default: auto
credits:
title: Credits
type: integer
readOnly: true
requestBodies:
MiniMaxH3:
content:
application/json:
schema:
$ref: '#/components/schemas/MiniMaxH3'
required: true
securitySchemes:
ApiKey:
type: apiKey
name: Authorization
in: header
description: Enter 'Bearer sk-cs-...' (your API key from Account → API Access).
x-refined-from:
- craftstory-com-swagger.json
- craftstory-com-openapi.yml