Run inference on your tuned models or base open source models.
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/lamini:lamini-completions-api"curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
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: Lamini Completions API
description: LLM inference and tuning for the enterprise. Factual LLMs. Classifier and embeddings. Deployed anywhere in 10 min.
version: 1.13.6
security:
- APIKeyAuth: []
tags:
- name: Completions
description: Run inference on your tuned models or base open source models.
paths:
/v1/batch_completions:
post:
tags:
- Completions
summary: Make a batch inference request
description: Kicks off batch inference for multiple prompts. Results can be retrieved using the job id returned on success.
operationId: batch_completion_v1_batch_completions_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BatchCompletionsPayload'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/BatchInitialResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- API Key Auth: []
parameters:
- name: Authorization
in: header
required: true
schema:
type: string
description: API key for authentication
/v1/batch_completions/{id}/result:
get:
tags:
- Completions
summary: Get the inference results for a batch request
description: Get the inference results for a batch request by passing in the ID of the batch request.
operationId: batch_completion_result_v1_batch_completions__id__result_get
parameters:
- required: true
schema:
type: string
title: Id
name: id
in: path
- name: Authorization
in: header
required: true
schema:
type: string
description: API key for authentication
responses:
'200':
description: Successful response
content:
application/json:
schema:
$ref: '#/components/schemas/CompletionsWithFinishReasonResponse'
example:
outputs:
- text: This is one inference output.
- text: This is another output.
finish_reason: stop
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- API Key Auth: []
/v2/completions:
post:
tags:
- Completions
summary: Generate completions for prompts
description: Generate an LLM inference response to a prompt, optionally with a specified JSON output structure, with a `finish_reason` field in the response indicating the end state for each inference request.
operationId: completions_v2_completions_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CompletionsPayload'
required: true
responses:
'200':
description: Successful response
content:
application/json:
schema:
$ref: '#/components/schemas/CompletionsWithFinishReasonResponse'
example:
outputs:
- text: This is one inference output.
- text: This is another output.
finish_reason: stop
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- API Key Auth: []
parameters:
- name: Authorization
in: header
required: true
schema:
type: string
description: API key for authentication
/v3/streaming_completions:
post:
tags:
- Completions
summary: Create a streaming inference completion
description: Generate an LLM inference response to a prompt, optionally with a specified JSON output structure, with a `finish_reason` field in the response indicating the end state for each inference request.
operationId: streaming_completions_v3_streaming_completions_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/V3StreamingCompletionsPayload'
required: true
responses:
'200':
description: The streaming inference completion.
content:
application/json:
schema:
$ref: '#/components/schemas/BatchInitialResponse'
example:
id: 2af8bd94f5118480a0c7be525c26d1a9
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- API Key Auth: []
parameters:
- name: Authorization
in: header
required: true
schema:
type: string
description: API key for authentication
/v3/streaming_completions/{id}/result:
get:
tags:
- Completions
summary: Get the latest output of a streaming inference completion
description: Get the result of a streaming completion by ID
operationId: streaming_completion_result_v3_streaming_completions__id__result_get
parameters:
- required: true
schema:
type: string
title: Id
name: id
in: path
- name: Authorization
in: header
required: true
schema:
type: string
description: API key for authentication
responses:
'200':
description: Successful response
content:
application/json:
schema:
$ref: '#/components/schemas/CompletionsWithFinishReasonResponse'
example:
outputs:
- text: This is one inference output.
- text: This is another output.
finish_reason: stop
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- API Key Auth: []
components:
schemas:
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
type: object
required:
- loc
- msg
- type
title: ValidationError
CompletionsWithFinishReasonResponse:
properties:
outputs:
items:
additionalProperties:
type: string
type: object
type: array
title: Outputs
description: The inference outputs for the given prompt(s).
finish_reason:
items:
$ref: '#/components/schemas/FinishReason'
type: array
title: Finish Reason
description: The final state for each inference request.
type: object
required:
- outputs
- finish_reason
title: CompletionsWithFinishReasonResponse
V3StreamingCompletionsPayload:
properties:
model_name:
type: string
title: Model Name
description: The name of your base model.
example: meta-llama/Llama-3.2-3B-Instruct
prompt:
type: string
title: Prompt
description: A single prompt for the model.
example: What is the hottest day of the year?
output_type:
additionalProperties:
anyOf:
- type: string
- items:
type: integer
type: array
- items:
type: string
type: array
type: object
title: Output Type
example:
answer: str
summary: Type schema of the output. Valid types are 'str', 'int', 'float', and 'bool'.
max_new_tokens:
type: integer
title: Max New Tokens
description: The maximum number of tokens to generate. Should be just large enough to accommodate the output you need - a lower value allows better pipeline execution speed and quality of service for batched requests.
example: 500
type: object
required:
- model_name
- prompt
title: V3StreamingCompletionsPayload
BatchCompletionsPayload:
properties:
model_name:
type: string
title: Model Name
description: The name of your base model.
example: meta-llama/Llama-3.2-3B-Instruct
prompt:
items:
type: string
type: array
title: Prompt
description: Multiple prompts for the model, presented as a list of strings for batch processing.
example:
- What is the hottest day of the year?
- What is the coldest day of the year?
output_type:
additionalProperties:
anyOf:
- type: string
- items:
type: integer
type: array
- items:
type: string
type: array
type: object
title: Output Type
example:
answer: str
summary: Type schema of the output. Valid types are 'str', 'int', 'float', and 'bool'.
max_new_tokens:
type: integer
title: Max New Tokens
description: The maximum number of tokens to generate. Should be just large enough to accommodate the output you need - a lower value allows better pipeline execution speed and quality of service for batched requests.
example: 500
max_tokens:
type: integer
title: Max Tokens
reservation_id:
type: integer
title: Reservation Id
type: object
required:
- model_name
- prompt
title: BatchCompletionsPayload
CompletionsPayload:
properties:
model_name:
type: string
title: Model Name
description: The name of your base model.
example: meta-llama/Llama-3.2-3B-Instruct
prompt:
anyOf:
- type: string
- items:
type: string
type: array
title: Prompt
description: The prompt for the model. Can be a single string or a list of strings for batch processing.
example: What is the hottest day of the year?
output_type:
additionalProperties:
anyOf:
- type: string
- items:
type: integer
type: array
- items:
type: string
type: array
type: object
title: Output Type
example:
answer: str
summary: Type schema of the output. Valid types are 'str', 'int', 'float', and 'bool'.
max_tokens:
type: integer
title: Max Tokens
description: The maximum number of tokens to generate.
max_new_tokens:
type: integer
title: Max New Tokens
description: The maximum number of tokens to generate. Should be just large enough to accommodate the output you need - a lower value allows better pipeline execution speed and quality of service for batched requests.
example: 500
reservation_id:
type: integer
title: Reservation Id
type: object
required:
- model_name
- prompt
title: CompletionsPayload
FinishReason:
type: string
enum:
- stop
- length
- timeout
title: FinishReason
description: 'Indicates the ending state of the inference request.
`stop`: The model completed the response with an EOS or equivalent token. This means the model finished generating the response.
`length`: The response reached the maximum number of tokens as set by max_new_tokens or other token limit.
`timeout`: The time taken to generate the response exceeded the configured Lamini Platform inference timeout. See [Performance](https://docs.lamini.ai/inference/performance/) for how to use this information to debug problems and improve performance.'
BatchInitialResponse:
properties:
id:
type: string
title: Id
description: The ID of the batch request.
example: 2af8bd94f5118480a0c7be525c26d1a9
type: object
required:
- id
title: BatchInitialResponse
securitySchemes:
APIKeyAuth:
type: apiKey
in: header
name: Authorization
description: Enter your API token. Get your API key from http://localhost:5001/account
x-provenance:
method: harvested
publisher: Lamini
source: https://docs.lamini.ai/openapi.json
note: split by refine-openapis from the provider's own published document, verified by fetch (openapi/_original/*.fetch.json);
stamped by stamp-openapi-provenance.py (roadmap#793)