Messages (Anthropic API)

Anthropic Messages API-compatible endpoint for native Claude SDK integration.

POST /v1/messages

Send a chat completion using the Anthropic Messages API format. This endpoint runs through the exact same pipeline as /v1/chat/completions — same BYOK, budget, guardian, guardrails, tool firewall, audit, and routing — but accepts and returns Anthropic-format requests and responses.

This allows tools that natively speak the Anthropic Messages API (e.g., Claude SDKs, Microsoft 365 Copilot add-ins, custom integrations) to connect to BrainstormRouter without any format conversion on the client side.

Request

curl https://api.brainstormrouter.com/v1/messages \
  -H "Authorization: Bearer br_live_..." \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "anthropic/claude-sonnet-4-20250514",
    "max_tokens": 1024,
    "system": "You are a helpful assistant.",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in one sentence."}
    ]
  }'

Response (Non-Streaming)

{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "model": "anthropic/claude-sonnet-4-20250514",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "content": [
    {
      "type": "text",
      "text": "Quantum computing uses quantum bits that can exist in multiple states simultaneously, enabling parallel processing of complex calculations."
    }
  ],
  "usage": {
    "input_tokens": 25,
    "output_tokens": 28
  }
}

Streaming

Set "stream": true to receive Anthropic-format SSE events:

data: {"type":"message_start","message":{"id":"msg_abc123","type":"message","role":"assistant","content":[],"model":"anthropic/claude-sonnet-4-20250514","stop_reason":null,"usage":{"input_tokens":25,"output_tokens":0}}}

event: content_block_start
data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}

event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Quantum"}}

event: content_block_stop
data: {"type":"content_block_stop","index":0}

event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"output_tokens":28}}

event: message_stop
data: {"type":"message_stop"}

Cross-Provider Routing

You can route to any provider through this endpoint — not just Anthropic. The request format is always Anthropic, but the model can be any BrainstormRouter model:

{
  "model": "openai/gpt-4o",
  "max_tokens": 1024,
  "messages": [{ "role": "user", "content": "Hello" }]
}

The response will always be in Anthropic Messages format regardless of which provider handled the request.

Tool Use

{
  "model": "anthropic/claude-sonnet-4-20250514",
  "max_tokens": 1024,
  "tools": [
    {
      "name": "get_weather",
      "description": "Get current weather for a city",
      "input_schema": {
        "type": "object",
        "properties": {
          "city": { "type": "string" }
        },
        "required": ["city"]
      }
    }
  ],
  "messages": [{ "role": "user", "content": "What's the weather in SF?" }]
}

BrainstormRouter Headers

All standard X-BR-* headers are present on /v1/messages responses, confirming the full pipeline ran:

• X-BR-Guardian-Status — Guardian processing status
• X-BR-Estimated-Cost / X-BR-Actual-Cost — Cost tracking
• X-BR-Routing-Overhead-Ms — Routing overhead latency
• X-BR-Total-Latency-Ms — Total request latency

Authentication

Same as all /v1/* endpoints: Authorization: Bearer br_live_...

Required RBAC permission: router.write (same as /v1/chat/completions).