Messages

Create Message (Anthropic Format)

post

https://api.fastrouter.ai/api/v1https://api.fastrouter.ai/v1

/messages

Creates a message using Anthropic's native Messages API format. Supports all Claude models through FastRouter with full feature parity including streaming, tool use, extended thinking, and vision.

Available at both:

• POST https://api.fastrouter.ai/api/v1/messages

• POST https://api.fastrouter.ai/v1/messages

Authentication: Use your FastRouter API key via either:

• x-api-key: YOUR_API_KEY (Anthropic style)

• Authorization: Bearer YOUR_API_KEY (OpenAI style)

Streaming: Set stream: true to receive Server-Sent Events (SSE) with Anthropic's native streaming format (message_start, content_block_start, content_block_delta, message_delta, etc.).

Cost tracking: The response usage object includes a cost field showing credits consumed.

Drop-in replacement: This endpoint is a drop-in replacement for Anthropic's /v1/messages API. Simply change the base URL to https://api.fastrouter.ai and use your FastRouter API key.

Authorizations

bearerAuthapiKeyAuth

AuthorizationstringRequired

FastRouter API Key. Get yours at https://fastrouter.ai

Format: Authorization: Bearer YOUR_API_KEY

Body

application/json

modelstringRequired

Model ID. Use anthropic/ prefix or bare Anthropic model name. Examples: anthropic/claude-sonnet-4-20250514, claude-sonnet-4-20250514, anthropic/claude-opus-4-20250514

Example: anthropic/claude-sonnet-4-20250514

max_tokensintegerRequired

The maximum number of tokens to generate before stopping. Required for all requests.

Example: 1024

systemone ofOptional

System prompt. Can be a string or an array of content blocks for advanced use cases like prompt caching.

stringOptional

or

temperaturenumber · max: 1Optional

Amount of randomness injected into the response. Ranges from 0.0 to 1.0.

Example: 1

top_pnumberOptional

Nucleus sampling parameter. Use a lower value to ignore less probable options.

Example: 0.999

top_kintegerOptional

Only sample from the top K options for each subsequent token.

stop_sequencesstring[]Optional

Custom text sequences that will cause the model to stop generating.

streambooleanOptional

Whether to stream the response using Server-Sent Events (SSE).

Default: falseExample: false

Responses

200

Message created successfully

application/json

400

Bad Request - The request is malformed. This could be due to missing parameters, invalid formats, or CORS issues.

application/json

401

Invalid Credentials - Your API key is invalid, disabled, or your OAuth session has expired. Check your credentials.

application/json

402

Insufficient Credits - Your account or API key has run out of credits. Add more credits and retry the request.

application/json

429

Rate Limited - You have exceeded your request limits (TPM/RPM). Slow down or increase your limits.

application/json

500Error

502

Model Down / Invalid Response - The selected model is currently unavailable or returned an invalid response. Retry or use fallback models.

application/json

post

/messages

HTTPcURLJavaScriptPython

POST /api/v1/messages HTTP/1.1
Host: api.fastrouter.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 125

{
  "model": "anthropic/claude-sonnet-4-20250514",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello, how are you?"
    }
  ]
}

Basic Text MessageWith System PromptStreaming ResponseExtended ThinkingTool Use

{
  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! I'm doing well, thank you for asking. How can I help you today?"
    }
  ],
  "model": "claude-sonnet-4-20250514",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 14,
    "output_tokens": 18,
    "cost": 0.000234
  }
}