API docs by Redocly

MLPA (1.0.0)

Download OpenAPI specification:

A proxy to verify App Attest/FxA payloads and proxy requests through LiteLLM.

Health

Health check endpoints.

Liveness Probe

Responses

Response samples

Content type
application/json
null

Readiness Probe

Responses

Response samples

Content type
application/json
null

Metrics

Prometheus metrics endpoints.

Get Metrics

Responses

Response samples

Content type
application/json
null

App Attest

Endpoints for verifying App Attest payloads.

Get Challenge

query Parameters
key_id_b64
required
string (Key Id B64)

Responses

Response samples

Content type
application/json
null

Attest

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Use-Qa-Certificates (boolean) or Use-Qa-Certificates (null) (Use-Qa-Certificates)

Responses

Response samples

Content type
application/json
null

LiteLLM

Endpoints for interacting with LiteLLM.

Chat Completion

Authorize first using App Attest or FxA. Pass the authorization header containing either the FxA token or the App Attest data JWT

header Parameters
authorization
required
string (Authorization)
service-type
required
string (ServiceType)
Enum: "ai" "s2s" "memories"
Use-App-Attest (boolean) or Use-App-Attest (null) (Use-App-Attest)
Use-Qa-Certificates (boolean) or Use-Qa-Certificates (null) (Use-Qa-Certificates)
Request Body schema: application/json
required
Stream (boolean) or Stream (null) (Stream)
Default: false
Array of objects (Messages)
Default: []
Model (string) or Model (null) (Model)
Default: "openai/gpt-4o"
Temperature (number) or Temperature (null) (Temperature)
Default: 0.1
Max Completion Tokens (integer) or Max Completion Tokens (null) (Max Completion Tokens)
Default: 1024
Top P (number) or Top P (null) (Top P)
Default: 0.01
Mock Response (string) or Mock Response (null) (Mock Response)

Responses

Request samples

Content type
application/json
{
  • "stream": false,
  • "messages": [ ],
  • "model": "openai/gpt-4o",
  • "temperature": 0.1,
  • "max_completion_tokens": 1024,
  • "top_p": 0.01,
  • "mock_response": "string"
}

Response samples

Content type
application/json
null

Mock

Mock endpoints for testing purposes.

Chat Completion

Mock LiteLLM endpoint with simulated latency.

header Parameters
authorization
required
string (Authorization)
service-type
required
string (ServiceType)
Enum: "ai" "s2s" "memories"
Use-App-Attest (boolean) or Use-App-Attest (null) (Use-App-Attest)
Use-Qa-Certificates (boolean) or Use-Qa-Certificates (null) (Use-Qa-Certificates)
Request Body schema: application/json
required
Stream (boolean) or Stream (null) (Stream)
Default: false
Array of objects (Messages)
Default: []
Model (string) or Model (null) (Model)
Default: "openai/gpt-4o"
Temperature (number) or Temperature (null) (Temperature)
Default: 0.1
Max Completion Tokens (integer) or Max Completion Tokens (null) (Max Completion Tokens)
Default: 1024
Top P (number) or Top P (null) (Top P)
Default: 0.01
Mock Response (string) or Mock Response (null) (Mock Response)

Responses

Request samples

Content type
application/json
{
  • "stream": false,
  • "messages": [ ],
  • "model": "openai/gpt-4o",
  • "temperature": 0.1,
  • "max_completion_tokens": 1024,
  • "top_p": 0.01,
  • "mock_response": "string"
}

Response samples

Content type
application/json
null

Chat Completion No Auth

Mock LiteLLM endpoint with simulated latency and JWT-only token validation (no POST calls).

header Parameters
required
Authorization (string) or Authorization (null) (Authorization)
Request Body schema: application/json
required
Stream (boolean) or Stream (null) (Stream)
Default: false
Array of objects (Messages)
Default: []
Model (string) or Model (null) (Model)
Default: "openai/gpt-4o"
Temperature (number) or Temperature (null) (Temperature)
Default: 0.1
Max Completion Tokens (integer) or Max Completion Tokens (null) (Max Completion Tokens)
Default: 1024
Top P (number) or Top P (null) (Top P)
Default: 0.01
Mock Response (string) or Mock Response (null) (Mock Response)

Responses

Request samples

Content type
application/json
{
  • "stream": false,
  • "messages": [ ],
  • "model": "openai/gpt-4o",
  • "temperature": 0.1,
  • "max_completion_tokens": 1024,
  • "top_p": 0.01,
  • "mock_response": "string"
}

Response samples

Content type
application/json
null

User Management

Endpoints for managing user blocking status.

List Users

List all users with pagination support.

query Parameters
limit
integer (Limit) [ 1 .. 200 ]
Default: 50
offset
integer (Offset) >= 0
Default: 0
header Parameters
master-key
required
string (Master Key)

Responses

Response samples

Content type
application/json
null

Block User

Block a user by their user_id.

path Parameters
user_id
required
string (User Id)
header Parameters
master-key
required
string (Master Key)

Responses

Response samples

Content type
application/json
null

Unblock User

Unblock a user by their user_id.

path Parameters
user_id
required
string (User Id)
header Parameters
master-key
required
string (Master Key)

Responses

Response samples

Content type
application/json
null

User

User Info

path Parameters
user_id
required
string (User Id)

Responses

Response samples

Content type
application/json
null