Deeplogix - API Documentation

Authentication

Deeplogix supports two authentication methods. Most API calls require Bearer token authentication. Public endpoints (catalog, providers) require no authentication.

Bearer Token

Pass your API key in the Authorization header.

Authorization: Bearer YOUR_API_KEY

Obtain your key from the account dashboard or via POST /user/api-keys.

Cookie Session

Authenticate via a session cookie named session. Used primarily by browser-based integrations and the IFTTT connector.

Set automatically after a successful login flow.

Quickstart

From zero to inference in two API calls - no GPU setup, no model hosting required.

01

Browse available models

Call GET /public/catalog?is_live=true to list all available models. No API key required. Each model returns an id (UUID) you'll use for inference.

02

Get your API key

Sign in to your Deeplogix account and generate an API key from the dashboard, or call POST /user/api-keys with a valid session.

03

Run inference

POST to /model/{model_id}/chat with your Bearer token and message. That's it.

// 1. Find a live model (no auth required)
const catalog = await fetch(
  'https://deeplogix.io/api/public/catalog?is_live=true'
)
const { data } = await catalog.json()
const modelId = data.models[0].id

// 2. Run inference (Bearer token required)
const res = await fetch(
  `https://deeplogix.io/api/model/${modelId}/chat`,
  {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'Authorization': 'Bearer YOUR_API_KEY'
    },
    body: JSON.stringify({ message: 'Summarize this document...' })
  }
)
const result = await res.json()

Health

Monitor server, database, and Redis status. No authentication required.

GET /health Server, database, and Redis health ▼

Returns health status of the server and all connected services including database and Redis. No authentication required.

Responses

200 object All services healthy. Returns status, timestamp, uptime (seconds), and per-service latency.

503 object One or more services unhealthy. Same structure with error details per service.

// 200 Response
{
  "status": "healthy",
  "timestamp": "2026-04-20T12:00:00Z",
  "uptime": 86400,
  "services": {
    "database": { "status": "healthy", "latency": 3.2 },
    "redis": { "status": "healthy", "latency": 0.8 }
  }
}

GET / Uptime check ▼

Simple uptime check. Returns a boolean status. No authentication required.

{ "status": true }

Public endpoints

Browse available models and providers. No authentication required.

GET /public/catalog List models ▼

Returns a filtered list of available models. All query parameters are optional.

Query Parameters

provider optional string Filter by provider name (e.g. "Ollama").

host_id optional uuid Filter by host identifier.

name optional string Filter by model name.

is_live optional boolean Filter to only live/active models. Pass true for production use.

// 200 Response
{
  "ok": true,
  "data": {
    "models": [
      {
        "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
        "name": "mistral-7b-instruct",
        "provider": "Ollama",
        "ts_created": "2026-01-15T08:30:00Z",
        "host_id": "7c8d9e0f-1234-5678-abcd-ef0123456789",
        "is_living": true
      }
    ],
    "count": 100,
    "limit": 10
  }
}

GET /public/model/{id} Get model details ▼

Returns detailed information about a specific model by its UUID.

Path Parameters

id required uuid Unique identifier of the model. Obtain from GET /public/catalog.

GET /public/model-providers List providers ▼

Returns a list of all supported model providers available on the platform.

{
  "ok": true,
  "data": [
    { "provider": "Ollama" }
  ]
}

Model inference

Run inference against any available model. All inference endpoints require Bearer token authentication.

POST /model/{id}/chat Run inference ▼

Send a message to a specific model and receive a generated response. This is the primary inference endpoint.

Path Parameters

id required uuid Model UUID from GET /public/catalog.

Request Body

message required string The input message or prompt to send to the model.

// Request
const res = await fetch(
  'https://deeplogix.io/api/model/MODEL_UUID/chat',
  {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'Authorization': 'Bearer YOUR_API_KEY'
    },
    body: JSON.stringify({
      message: 'Explain the key points of this contract...'
    })
  }
)

GET /model/{id}/info Get model metadata ▼

Returns metadata about a specific model. Requires authentication.

Path Parameters

id required uuid The model UUID.

POST /model/{id}/load Load model onto host ▼

Loads a model onto a host to make it available for inference. Call this before running inference if the model is not currently live.

POST /model/{id}/unload Unload model from host ▼

Unloads a model from its host, freeing resources. The model will no longer be available for inference until reloaded.

User & account

Manage your account, API keys, and OAuth applications. All endpoints require authentication.

GET /user/info Get current user ▼

Returns profile information for the currently authenticated user.

{
  "ok": true,
  "data": {
    "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
    "email": "user@example.com",
    "ts_created": "2026-01-01T00:00:00Z"
  }
}

GET /user/api-keys List API keys ▼

Returns all API keys associated with the authenticated user's account.

POST /user/api-keys Create API key ▼

Creates a new API key for the authenticated user. Store the returned key securely — it will not be shown again.

DELETE /user/api-keys/{id} Delete API key ▼

Permanently deletes the specified API key. Any applications using this key will immediately lose access.

Path Parameters

id required uuid The API key identifier to delete.

OAuth applications

Create and manage OAuth 2.0 applications for third-party integrations. Requires authentication.

GET /user/oauth List OAuth apps ▼

Returns all OAuth applications created by the authenticated user.

POST /user/oauth Create OAuth app ▼

Creates a new OAuth application. Returns a client_secret — store it securely as it cannot be retrieved again.

Request Body

name required string Display name of the OAuth application.

redirect_uris required string[] List of allowed redirect URIs (must be valid URIs).

scopes optional string[] List of permission scopes the application can request.

// 201 Response
{
  "ok": true,
  "data": {
    "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
    "client_secret": "sk_live_..."
  }
}

POST /user/oauth/{id}/reset Reset client secret ▼

Resets and reissues the client_secret for the specified OAuth application. The previous secret is immediately invalidated.

Error reference

All errors return consistent JSON with a status code and error identifier. Error codes follow the pattern E_<FIELD>-<TYPE>.

Status	Code	Description
200	-	Successful response. Returns `ok: true` and a `data` object.
400	E_<FIELD>-BAD_REQUEST	The request is malformed or contains invalid parameters. Check field names and types.
401	Unauthorized	Missing or invalid Bearer token. Ensure your API key is correctly passed in the Authorization header.
403	E_<FIELD>-FORBIDDEN	Authenticated but not permitted to access this resource.
404	E_<FIELD>-NOT_FOUND	The requested resource does not exist. Verify the UUID or path parameter.
500	Internal Server Error	An unexpected server error occurred. If this persists, contact support.
503	Service Unavailable	One or more dependent services (database, Redis) are unhealthy. Check `GET /health` for details.

Deeplogix API

Authentication

Bearer Token

Cookie Session

Quickstart

Browse available models

Get your API key

Run inference

Health

Public endpoints

Model inference

User & account

OAuth applications

Error reference