Anthropic Messages

POST https://api.routerplex.com/v1/messages

RouterPlex accepts Anthropic's Messages API request format and returns Anthropic-format responses for every chat model in the catalog — Claude, GPT, Gemini, DeepSeek, Kimi, Qwen, and more. The same RouterPlex key and prepaid balance work across both API formats.

Before you start #

These examples run on macOS, Linux, and Windows. Set your key and prepare your environment first.

For Python, install with .venv/bin/python -m pip install --upgrade anthropic on macOS/Linux or .\.venv\Scripts\python.exe -m pip install --upgrade anthropic in PowerShell. Save the Python example as messages.py and run it with that same Python executable.

For JavaScript, install @anthropic-ai/sdk with npm install @anthropic-ai/sdk on macOS/Linux or npm.cmd install @anthropic-ai/sdk in PowerShell. The TypeScript example also runs as a .mjs file with node messages.mjs.

curl — macOS and Linux #

curl https://api.routerplex.com/v1/messages \
  -H "x-api-key: $ROUTERPLEX_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "max_tokens": 256,
    "messages": [{"role": "user", "content": "Explain HTTP in one line"}]
  }'

Windows PowerShell #

$body = @{ model = 'claude-sonnet-4-6'; max_tokens = 256; messages = @(@{ role = 'user'; content = 'Reply with exactly: RouterPlex connected.' }) } | ConvertTo-Json -Depth 5
Invoke-RestMethod -Uri 'https://api.routerplex.com/v1/messages' -Method Post -Headers @{ 'x-api-key' = $env:ROUTERPLEX_API_KEY; 'anthropic-version' = '2023-06-01' } -ContentType 'application/json' -Body $body

Authorization: Bearer $ROUTERPLEX_API_KEY also works if your HTTP client already uses bearer authentication.

Python SDK #

import os
from anthropic import Anthropic
 
client = Anthropic(
    base_url="https://api.routerplex.com",
    api_key=os.environ["ROUTERPLEX_API_KEY"],
)
 
message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=256,
    messages=[{"role": "user", "content": "Explain HTTP in one line"}],
)
print(message.content[0].text)

TypeScript SDK #

import Anthropic from "@anthropic-ai/sdk";
 
const client = new Anthropic({
  baseURL: "https://api.routerplex.com",
  apiKey: process.env.ROUTERPLEX_API_KEY,
});
 
const message = await client.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 256,
  messages: [{ role: "user", content: "Explain HTTP in one line" }],
});
console.log(message.content);

Streaming #

Set stream: true or use the Anthropic SDK's streaming helper. RouterPlex returns Anthropic SSE events such as message_start, content_block_delta, and message_stop, including when the selected model is not a Claude model.

Which format should I use? #

Both formats reach the same 63 chat models and deduct from the same balance. gpt-image-2 is image-generation only and uses /v1/images/generations, not a chat endpoint. Tool use, vision, thinking, and structured-output support still depend on the selected model.

Confirm the returned text and the matching request in Usage. Official SDK references: Python, JavaScript/TypeScript.