mammoth-io LLM API
The LLM API from mammoth-io — 1 operation(s) for llm.
The LLM API from mammoth-io — 1 operation(s) for llm.
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/mammoth-io:mammoth-io-llm-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: Mammoth Io LLM API
version: 0.1.0
contact:
name: Mammoth Analytics
url: https://mammoth.io
email: support@mammoth.io
description: 'Operations tagged LLM across 2 of this provider''s published API definitions: app.mammoth.io-openapi.json, mammoth-io-openapi.json. Each path carries the servers of the definition it was published in.'
servers:
- url: /api/v2
security:
- bearerAuth: []
- apiKey: []
apiSecret: []
workspaceId: []
tags:
- name: LLM
paths:
/workspaces/{workspace_id}/llm:
post:
tags:
- LLM
summary: Trigger an LLM-based task for a workspace
description: Initiates an LLM-powered task. The behavior and execution flow vary depending on the `type` field in the request body.
operationId: RunLlmTask
parameters:
- name: workspace_id
in: path
schema:
type: integer
minimum: 1.0
title: Workspace ID
description: Workspace refers to a collection of projects. Workspace ID is unique identifier for workspace.
examples:
- 4
description: Workspace refers to a collection of projects. Workspace ID is unique identifier for workspace.
required: true
deprecated: false
examples:
workspace_id-example-1:
summary: Sample workspace ID
value: 4
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/UnifiedLlmTaskSpec'
required: true
responses:
'201':
description: Document created, URL follows
headers: {}
content:
application/json:
schema:
$ref: '#/components/schemas/JobResponse'
'400':
description: Bad request syntax or unsupported method
content:
application/json:
schema:
oneOf:
- properties:
status_code:
type: integer
detail:
type: string
extra:
additionalProperties: {}
type:
- 'null'
- object
- array
type: object
required:
- detail
- status_code
description: Client Error
examples:
- status_code: 400
detail: Bad Request
extra: {}
- properties:
status_code:
type: integer
detail:
type: string
extra:
additionalProperties: {}
type:
- 'null'
- object
- array
type: object
required:
- detail
- status_code
description: Validation Exception
examples:
- status_code: 400
detail: Bad Request
extra: {}
'403':
description: Request forbidden -- authorization will not help
content:
application/json:
schema:
properties:
status_code:
type: integer
detail:
type: string
extra:
additionalProperties: {}
type:
- 'null'
- object
- array
type: object
required:
- detail
- status_code
description: Authorization Exception
examples:
- status_code: 403
detail: Forbidden
extra: {}
'202':
description: Successfully Submitted
content:
application/json:
schema:
$ref: '#/components/schemas/JobResponse'
deprecated: false
servers:
- url: /api/v2
components:
schemas:
JobSchema:
properties:
id:
type: integer
minimum: 0.0
title: Job id
examples:
- value:
id: 10
status:
type: string
enum:
- success
- failure
- processing
- error
title: Job status
description: Job status can be success, failure or processing
examples:
- value:
status: success
response:
oneOf:
- type: object
- type: array
description: Result of async task is stored in response
examples:
- value:
response:
object: some object
last_updated_at:
type: string
format: date-time
title: Job last updated at
description: Job last updated at is the time when Job status was last updated
examples:
- value:
last_updated_at: '2021-08-10T10:00:00'
created_at:
type: string
format: date-time
title: Job created at
description: Create at is time when async task was created
examples:
- value:
created_at: '2021-08-10T10:00:00'
path:
type: string
title: Job path
description: API request path of the Job operation
examples:
- value:
path: /api/v2/dataviews/1
operation:
type: string
title: Job operation
description: Operation is async task name which Job is tracking
examples:
- value:
operation: post_modification_pipeline_execution
type: object
required:
- created_at
- id
- last_updated_at
- operation
- path
- response
- status
title: JobSchema
GenerateSummaryParams:
properties:
object_id:
type: integer
minimum: 1.0
title: Object ID
description: Unique identifier of the object (dataview, datasource, folder, etc.). Must be a positive integer.
object_type:
type: string
title: Object Type
description: Type of the object (dataview, datasource, label, project, workspace, etc.)
mode:
type: string
enum:
- llm
- raw
title: Mode
description: Whether to generate summary using LLM ('llm') or return raw summary ('raw')
default: raw
type: object
required:
- object_id
- object_type
title: GenerateSummaryParams
GenerateDatasetParams:
properties:
intent:
type: string
minLength: 1
title: Prompt
description: User prompt describing the dataset to be generated
examples:
- Generate data from a manufacturing facility
row_count:
oneOf:
- type: integer
- type: 'null'
maximum: 500
minimum: 1
title: Row Count
description: Number of rows to generate (1-500)
examples:
- 20
type: object
required:
- intent
title: GenerateDatasetParams
OptimisePipelineParams:
properties:
object_id:
type: integer
minimum: 1.0
title: Object ID
description: Unique identifier of the object (dataview, datasource, folder, etc.). Must be a positive integer.
object_type:
type: string
const: dataview
title: Object Type
description: Type of the object to optimise
type: object
required:
- object_id
- object_type
title: OptimisePipelineParams
JobResponse:
properties:
job:
$ref: '#/components/schemas/JobSchema'
type: object
required:
- job
title: JobResponse
RenameColumnsParams:
properties:
project_id:
type: integer
minimum: 1.0
title: Project ID
description: Unique identifier of the project. Must be a positive integer.
object_id:
type: integer
minimum: 1.0
title: Object ID
description: Unique identifier of the object (dataview, datasource, etc.). Must be a positive integer.
object_type:
type: string
const: datasource
title: Object Type
description: Type of the object. Only 'datasource' is supported.
transform_mode:
$ref: '#/components/schemas/TransformMode'
instruction:
oneOf:
- type: string
- type: 'null'
minLength: 1
title: Instruction
description: Natural language instruction for renaming columns. Required when transform_mode is 'instruction_based', ignored otherwise.
type: object
required:
- object_id
- object_type
- project_id
- transform_mode
title: RenameColumnsParams
TransformMode:
type: string
enum:
- snake_case
- camel_case
- instruction_based
title: TransformMode
description: 'Mode of renaming: ''snake_case'', ''camel_case'', or ''instruction_based'' (LLM-driven).'
UnifiedLlmTaskSpec:
properties:
type:
type: string
enum:
- rename_columns
- generate_dataset
- generate_summary
- optimise_pipeline
title: Task Type
description: Type of LLM operation to perform
params:
oneOf:
- $ref: '#/components/schemas/RenameColumnsParams'
- $ref: '#/components/schemas/OptimisePipelineParams'
- $ref: '#/components/schemas/GenerateSummaryParams'
- $ref: '#/components/schemas/GenerateDatasetParams'
title: Params
description: Encapsulated parameters for the selected task
type: object
required:
- params
- type
title: UnifiedLlmTaskSpec
description: LLM task submission request
examples:
- type: generate_summary
params:
object_id: 245
object_type: dataview
mode: llm
- type: generate_dataset
params:
intent: generate data from aerospace
row_count: 10
- type: rename_columns
params:
project_id: 1
object_id: 245
object_type: datasource
transform_mode: snake_case
- type: optimise_pipeline
params:
object_id: 245
object_type: dataview
securitySchemes:
bearerAuth:
type: http
description: 'Primary credential. Authorization: Bearer mm_<token>. The token is issued server-side and shown once at creation.'
scheme: bearer
apiKey:
type: apiKey
description: Deprecated — use bearerAuth.
name: X-API-KEY
in: header
apiSecret:
type: apiKey
description: Deprecated — use bearerAuth.
name: X-API-SECRET
in: header
workspaceId:
type: apiKey
description: Required with X-API-KEY and X-API-SECRET. Deprecated with them — use bearerAuth.
name: X-WORKSPACE-ID
in: header
x-refined-from:
- app.mammoth.io-openapi.json
- mammoth-io-openapi.json