Skip to content
AnyRouter

OpenAI Chat Completions

Keep your OpenAI SDK code. Change the base URL and key, and every model answers on the same request shape.

POSThttps://anyrouter.dev/api/v1/chat/completions
Start freeRead docs
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://anyrouter.dev/api/v1",
    api_key=os.environ["ANYROUTER_API_KEY"],
)

resp = client.chat.completions.create(
    model="anyrouter/auto",
    messages=[{"role": "user", "content": "Hi"}],
)
print(resp.choices[0].message.content)

What works

  • Streaming (SSE)
  • Tools / function calling
  • Structured output (response_format)
  • Reasoning effort
  • Image input on vision models