Router API Reference

WIP - THIS IS EARLY DRAFT

This document outlines the available RESTful API endpoints provided by a Cortensor Router Node. These endpoints enable interaction with sessions, tasks, and miners, making it easier to integrate AI inference functionality with traditional Web2 applications.

---

Authentication

All endpoints require API key authentication using a Bearer token in the Authorization header.

Header Format:

Authorization: Bearer <api_key>

Default Dev Token: default-dev-token

---

Endpoints

GET /api/v1/info

Returns basic router node metadata.

Example:

curl -X GET http://<router_host>:5010/api/v1/info \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <api_key>"

---

GET /api/v1/status

Returns current router node status and health.

Example:

curl -X GET http://<router_host>:5010/api/v1/status \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <api_key>"

---

GET /api/v1/miners

Lists all connected miners.

Example:

curl -X GET http://<router_host>:5010/api/v1/miners \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <api_key>"

---

GET /api/v1/sessions

Lists all currently active sessions.

Example:

curl -X GET http://<router_host>:5010/api/v1/sessions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <api_key>"

---

GET /api/v1/sessions/{sessionId}

Retrieves details about a specific session.

Path Parameter:

• sessionId: Numeric ID of the session

Example:

curl -X GET http://<router_host>:5010/api/v1/sessions/0 \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <api_key>"

---

GET /api/v1/tasks/{sessionId}/{taskId}

Returns details of a specific task within a session.

Path Parameters:

• sessionId: Numeric ID of the session

• taskId: Numeric ID of the task

Example:

curl -X GET http://<router_host>:5010/api/v1/tasks/0/0 \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <api_key>"

---

GET /api/v1/tasks/{sessionId}

Lists all tasks submitted under a specific session.

Path Parameter:

• sessionId: Numeric ID of the session

Example:

curl -X GET http://<router_host>:5010/api/v1/tasks/0 \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <api_key>"

---

POST /api/v1/completions/{sessionId}

Submits a prompt for AI inference using a specified session ID in the URL.

Path Parameter:

• sessionId: Numeric ID of the session

Request Body:

{
  "prompt": "Hello, how are you?",
  "stream": false,
  "timeout": 60
}

Example:

curl -X POST http://<router_host>:5010/api/v1/completions/0 \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <api_key>" \
  -d '{"prompt": "Hello, how are you?", "stream": false, "timeout": 60}'

---

POST /api/v1/completions

Submits a prompt with the session ID in the JSON payload instead of the URL.

Request Body:

{
  "session_id": 0,
  "prompt": "Hello, how are you?",
  "stream": false,
  "timeout": 60
}

Example:

curl -X POST http://<router_host>:5010/api/v1/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <api_key>" \
  -d '{"session_id": 0, "prompt": "Hello, how are you?", "stream": false, "timeout": 60}'

---

Notes

• The stream field enables real-time token-level streaming of AI completions.

• All endpoints are compatible with OpenAI-style interfaces, making integration intuitive for developers.

• Use this API to serve private inference traffic through your self-hosted Router Node