Router Management Chat and Route Test API

curl -X POST "https://router.example.com/v1/router/chat" \
  -H "Authorization: Bearer <api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "default",
    "messages": [{"role": "user", "content": "Hello router"}],
    "dry_run": true
  }'

{
  "decision": {
    "provider": "openai",
    "model": "gpt-4o",
    "recipe": "semantic-router"
  },
  "response": {
    "id": "chatcmpl-example",
    "choices": [
      {
        "index": 0,
        "message": {"role": "assistant", "content": "Hello! How can I help?"},
        "finish_reason": "stop"
      }
    ],
    "usage": {
      "prompt_tokens": 10,
      "completion_tokens": 8,
      "total_tokens": 18
    }
  }
}

curl -X POST "https://router.example.com/v1/router/chat" \
  -H "Authorization: Bearer <api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "default",
    "messages": [{"role": "user", "content": "Hello router"}],
    "dry_run": true
  }'

{
  "decision": {
    "provider": "openai",
    "model": "gpt-4o",
    "recipe": "semantic-router"
  },
  "response": {
    "id": "chatcmpl-example",
    "choices": [
      {
        "index": 0,
        "message": {"role": "assistant", "content": "Hello! How can I help?"},
        "finish_reason": "stop"
      }
    ],
    "usage": {
      "prompt_tokens": 10,
      "completion_tokens": 8,
      "total_tokens": 18
    }
  }
}

The management Chat endpoint lets you test how a chat request would be routed through the Aria Compute ROUTER. It accepts the same request body as /v1/chat/completions and adds an optional dry_run flag. Use it to validate routing rules, inspect provider selection, and debug recipes without emitting downstream requests. This endpoint returns both the routing decision and, when not in dry-run mode, the downstream provider response.

Endpoint

POST /v1/router/chat

Authentication

Authenticate with a session cookie or pass Authorization: Bearer <api-key>.

Request Body

string

required

Target model or virtual model name.

array

required

Conversation messages in standard chat-completion shape.

boolean

When true, the router computes the route decision without sending the request to the provider.

number

Sampling temperature.

integer

Maximum tokens to generate.

Response

object

Routing decision produced by the router.

Show properties

string

Selected provider name.

string

Resolved model name sent to the provider.

string

Recipe that matched this request.

object

Downstream provider response. Omitted when dry_run is true.

Show properties

string

Completion identifier.

array

Generated choices.

object

Token usage summary.

curl -X POST "https://router.example.com/v1/router/chat" \
  -H "Authorization: Bearer <api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "default",
    "messages": [{"role": "user", "content": "Hello router"}],
    "dry_run": true
  }'

{
  "decision": {
    "provider": "openai",
    "model": "gpt-4o",
    "recipe": "semantic-router"
  },
  "response": {
    "id": "chatcmpl-example",
    "choices": [
      {
        "index": 0,
        "message": {"role": "assistant", "content": "Hello! How can I help?"},
        "finish_reason": "stop"
      }
    ],
    "usage": {
      "prompt_tokens": 10,
      "completion_tokens": 8,
      "total_tokens": 18
    }
  }
}

PIN API

ROUTER API

AGENT API

Router Management Chat and Route Test API

Endpoint

Authentication

Request Body

Response

​Endpoint

​Authentication

​Request Body

​Response

Endpoint

Authentication

Request Body

Response