Chat

Chat completion endpoints (OpenAI-compatible).

List chat completions

get

List chat completions captured in telemetry, scoped to the authenticated project.

Authorizations

ApiKeyAuth

AuthorizationstringRequired

API key in Authorization header using Bearer .

Query parameters

limitinteger · min: 1 · max: 100OptionalDefault: 20

offsetintegerOptionalDefault: 0

modelstring · nullableOptional

containerstring · nullableOptional

orderstring · enumOptionalDefault: descPossible values:

Body

application/json

Other propertiesanyOptional

Responses

200

Successful Response

application/json

OpenAI-style list response for chat completions.

objectconst: listOptional

Object type identifier.

Default: list

totalintegerRequired

Total number of items available for this resource.

400

Bad Request

application/json

401

Unauthorized

application/json

403

Forbidden

application/json

422

Validation Error

application/json

429

Too Many Requests

application/json

500

Internal Server Error

application/json

501

Not Implemented

application/json

503

Upstream Unavailable

application/json

get/v1/chat/completions

HTTPcURLJavaScriptPython

GET /v1/chat/completions HTTP/1.1
Host: platform.maniac.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 38

{
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

{
  "object": "list",
  "data": [
    {
      "choices": [
        {
          "finish_reason": "stop",
          "index": 0,
          "message": {
            "content": "Hello!",
            "role": "assistant"
          }
        }
      ],
      "created": 1710000000,
      "id": "chatcmpl-123",
      "model": "openai/gpt-4o",
      "object": "chat.completion"
    }
  ],
  "total": 0
}

Create a chat completion

post

Create a chat completion using the specified model.

Supports both streaming and non-streaming responses and is compatible with OpenAI's chat completions API. Use a container slug (maniac:<container>) or an external slug (e.g. openai/gpt-4o). / and : are treated equivalently on input.

Authorizations

ApiKeyAuth

AuthorizationstringRequired

API key in Authorization header using Bearer .

Body

application/json

OpenAI-compatible chat completion request with Maniac extensions.

modelstring · nullableOptional

Model slug to use. Supports global slugs and container routes; / and : are treated equivalently on input.

Example: openai/gpt-4o

modelsstring[] · nullableOptional

Fallback models.

frequency_penaltynumber · nullableOptional

Frequency penalty.

logprobsboolean · nullableOptional

Include logprobs.

top_logprobsnumber · nullableOptional

Top logprobs.

max_completion_tokensnumber · nullableOptional

Max completion tokens.

max_tokensnumber · nullableOptional

Max tokens.

ninteger · nullableOptional

Number of chat completion choices to generate (OpenAI n).

presence_penaltynumber · nullableOptional

Presence penalty.

response_formatany of · nullableOptional

Response format.

or

or

seedinteger · nullableOptional

Random seed.

service_tierstring · enum · nullableOptional

Service tier hint (auto/default/flex/scale/priority).

Possible values:

stopany of · nullableOptional

Stop sequences.

stringOptional

or

string[]Optional

streamboolean · nullableOptional

Stream response.

Default: false

temperaturenumber · nullableOptional

Temperature.

tool_choiceany of · nullableOptional

Tool choice.

string · enumOptionalPossible values:

or

parallel_tool_callsboolean · nullableOptional

Whether the model may emit multiple tool calls in parallel.

top_pnumber · nullableOptional

Top p.

top_knumber · nullableOptional

Top-k sampling (OpenRouter / Anthropic / vLLM).

min_pnumber · nullableOptional

Min-p sampling cutoff (OpenRouter / vLLM).

top_anumber · nullableOptional

Top-a sampling cutoff (OpenRouter alternate sampler).

repetition_penaltynumber · nullableOptional

Repetition penalty (OpenRouter / non-OpenAI providers).

transformsstring[] · nullableOptional

OpenRouter transform pipeline names (e.g. 'middle-out').

presetstring · nullableOptional

OpenRouter preset name (server-side stored param bundle).

tagsstring[]Optional

Optional tags for tracking.

Example: []

storeboolean · nullableOptional

Whether to store the completion in the database.

Default: true

Responses

200

Server-Sent Events stream for streaming responses.

application/jsontext/event-stream

idstringRequired

Completion id.

creatednumberRequired

Creation timestamp (unix).

modelstringRequired

Model used.

objectconst: chat.completionOptional

Object type.

Default: chat.completion

providerstring · nullableOptional

Upstream provider name, if available.

containerstring · nullableOptional

Container label used for routing, if any.

400

Bad Request

application/json

401

Unauthorized

application/json

402

Payment Required

application/json

403

Forbidden

application/json

404

Not Found

application/json

409

Conflict

application/json

422

Validation Error

application/json

429

Too Many Requests

application/json

500

Internal Server Error

application/json

501

Not Implemented

application/json

503

Upstream Unavailable

application/json

post/v1/chat/completions

HTTPcURLJavaScriptPython

POST /v1/chat/completions HTTP/1.1
Host: platform.maniac.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 88

{
  "messages": [
    {
      "content": "Hello!",
      "role": "user"
    }
  ],
  "model": "openai/gpt-4o",
  "stream": false
}

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Hello!",
        "role": "assistant"
      }
    }
  ],
  "created": 1710000000,
  "id": "chatcmpl-123",
  "model": "openai/gpt-4o",
  "object": "chat.completion"
}

Get a chat completion

get

Fetch a single chat completion by id within the authenticated project.

Authorizations

ApiKeyAuth

AuthorizationstringRequired

API key in Authorization header using Bearer .

Path parameters

completion_idstringRequired

Responses

200

Successful Response

application/json

idstring · nullableOptional

Completion id.

createdany · nullableOptional

Creation timestamp (unix seconds).

modelstring · nullableOptional

Model slug used.

objectconst: chat.completionOptional

Object type.

Default: chat.completion

providerstring · nullableOptional

Upstream provider name, if available.

containerstring · nullableOptional

Container label used for routing, if any.

model_idstring · nullableOptional

Model ID (uuid).

spendnumber · nullableOptional

Estimated spend.

tagsstring[] · nullableOptional

Tags for this completion.

400

Bad Request

application/json

401

Unauthorized

application/json

403

Forbidden

application/json

404

Not Found

application/json

409

Conflict

application/json

422

Validation Error

application/json

429

Too Many Requests

application/json

500

Internal Server Error

application/json

501

Not Implemented

application/json

503

Upstream Unavailable

application/json

get/v1/chat/completions/{completion_id}

HTTPcURLJavaScriptPython

GET /v1/chat/completions/{completion_id} HTTP/1.1
Host: platform.maniac.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Hello!",
        "role": "assistant"
      }
    }
  ],
  "created": 1710000000,
  "id": "chatcmpl-123",
  "model": "openai/gpt-4o",
  "object": "chat.completion"
}

Register chat completion examples

post

Register completed chat examples for evaluation and analytics.

This endpoint accepts input/output pairs and stores them for later analysis, while aggregating usage metrics for reporting.

Authorizations

ApiKeyAuth

AuthorizationstringRequired

API key in Authorization header using Bearer .

Body

application/json

Register completed chat examples for evaluation or analytics.

containerstringRequired

Container label to associate these examples with.

Example: maniac:my-container

Responses

200

Successful Response

application/json

okbooleanRequired

Whether the register operation succeeded.

containerstringRequired

Container label used for registration.

400

Bad Request

application/json

401

Unauthorized

application/json

403

Forbidden

application/json

404

Not Found

application/json

409

Conflict

application/json

422

Validation Error

application/json

429

Too Many Requests

application/json

500

Internal Server Error

application/json

501

Not Implemented

application/json

503

Upstream Unavailable

application/json

post/v1/chat/completions/register

HTTPcURLJavaScriptPython

POST /v1/chat/completions/register HTTP/1.1
Host: platform.maniac.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 410

{
  "items": [
    {
      "input": {
        "messages": [
          {
            "content": "Hello!",
            "role": "user"
          }
        ],
        "model": "openai/gpt-4o",
        "stream": false
      },
      "output": {
        "choices": [
          {
            "finish_reason": "stop",
            "index": 0,
            "message": {
              "content": "Hello!",
              "role": "assistant"
            }
          }
        ],
        "created": 1710000000,
        "id": "chatcmpl-123",
        "model": "openai/gpt-4o",
        "object": "chat.completion"
      },
      "tags": [
        "text"
      ],
      "metadata": {
        "ANY_ADDITIONAL_PROPERTY": "anything"
      }
    }
  ],
  "container": "maniac:my-container"
}

{
  "container": "maniac:my-container",
  "errors": [],
  "ok": true,
  "summary": {
    "inserted": 10,
    "skipped": 0
  }
}