API Reference: Anthropic Messages

Endpoint & Headers

The gateway accepts standard Anthropic authentication headers (x-api-key) as well as standard Bearer tokens. Both /v1/messages and /messages are routed identically.

httpRequest

POST https://infinityrouter.qd.je/v1/messages
x-api-key: inf_live_...
anthropic-version: 2023-06-01
Content-Type: application/json

Request Body Parameters

Parameters
Parameter	Type	Required	Description
model	string	Yes	Canonical ID from the model catalog (e.g. claude-sonnet-5, deepseek-chat).
messages	array	Yes	Array of message objects with role (user or assistant) and content blocks.
max_tokens	integer	Yes	Maximum completion tokens to generate (enforced by the Messages specification).
system	string \| array	No	Top-level system instructions passed directly to models.
stream	boolean	No	When true, returns standard Anthropic SSE message stream events.
temperature	number	No	Sampling temperature between 0.0 and 1.0. Default 1.0.
tools	array	No	List of tool definitions with name, description, and input_schema.

Python Example (Anthropic SDK)

pythonanthropic_example.py

import os
from anthropic import Anthropic

client = Anthropic(
    base_url="https://infinityrouter.qd.je/v1",
    api_key=os.environ.get("INFINITY_API_KEY"),
)

message = client.messages.create(
    model="claude-sonnet-5",
    max_tokens=1024,
    system="You are a senior infrastructure engineer.",
    messages=[
        {"role": "user", "content": "How does multi-provider routing prevent downtime?"}
    ],
)

print(message.content[0].text)

TypeScript Example (Anthropic SDK)

typescriptanthropic_example.ts

import Anthropic from "@anthropic-ai/sdk";

const anthropic = new Anthropic({
  baseURL: "https://infinityrouter.qd.je/v1",
  apiKey: process.env.INFINITY_API_KEY,
});

async function main() {
  const message = await anthropic.messages.create({
    model: "claude-sonnet-5",
    max_tokens=1024,
    system: "You are a concise assistant.",
    messages: [{ role: "user", content: "Summarize AI cost optimization." }],
  });

  console.log(message.content[0]);
}

main();

Example Response (Non-Streaming)

json200 OK

{
  "id": "req_a1b2c3d4e5f6",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Multi-provider routing automatically switches to healthy alternative upstreams when a primary provider experiences downtime or rate limits."
    }
  ],
  "model": "claude-sonnet-5",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 18,
    "output_tokens": 26
  }
}

Response Status Codes

HTTP Status Codes
Status	Code	Description
200	OK	Successful completion or streaming message.
400	invalid_request	Malformed payload, missing max_tokens, or schema validation issue.
401	authentication_failed	Missing, invalid, or revoked API key.
402	insufficient_credits	Account balance cannot cover token reservation hold.
404	model_not_found	Requested canonical model ID does not exist.
429	rate_limited	Key throughput limit exceeded (returns Retry-After header).
502	upstream_failure	Downstream AI provider returned an unexpected error.
503	no_capacity	All upstream routes for requested model are currently unavailable.