Anthropic API

Anthropic Messages Endpoint

Router9 provides a native Anthropic-compatible endpoint for tools that use the Anthropic SDK directly.

POST /anthropic/v1/messages

Request Headers

Header	Required	Description
`x-api-key`	Yes	`sk-r9k-your-key`
`Content-Type`	Yes	`application/json`

Request Body

Parameter	Type	Required	Description
`model`	string	Yes	Model ID (e.g. `claude-3-sonnet`)
`max_tokens`	number	Yes	Maximum tokens to generate
`messages`	array	Yes	Conversation messages
`stream`	boolean	No	Enable streaming (default: `false`)

Example Request

curl https://api.router9.com/anthropic/v1/messages \
  -H "x-api-key: sk-r9k-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-3-sonnet",
    "max_tokens": 1024,
    "messages": [
      { "role": "user", "content": "Explain recursion briefly." }
    ]
  }'

Response

{
  "type": "message",
  "id": "msg-abc123",
  "content": [
    {
      "type": "text",
      "text": "Recursion is when a function calls itself to solve a problem by breaking it into smaller instances of the same problem, with a base case to stop the recursion."
    }
  ],
  "model": "claude-3-sonnet",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 12,
    "output_tokens": 38
  }
}

Error Response

{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "model, max_tokens, and messages are required"
  }
}

Streaming

Set stream: true to receive Anthropic-format streaming events. Router9 automatically transforms the upstream response into the correct Anthropic SSE format.

When to Use This Endpoint

Use /anthropic/v1/messages when:

Your application uses the Anthropic Python or TypeScript SDK
You need Anthropic-native response formats (content blocks, stop_reason, etc.)

For all other cases, use the Chat Completions endpoint which works with any OpenAI-compatible client.

On this page