Pay for the outcome.

Point an OpenAI client at one base URL. Every model, one wire format.

POST /v1/chat/completions

{
  "model": "openai/gpt-5.6-luna",
  "messages": [
    { "role": "user",
      "content": "In one sentence: what does a routing layer do?" }
  ],
  "max_tokens": 120
}

{
  "model": "openai/gpt-5.6-luna",
  "choices": [{
    "message": {
      "role": "assistant",
      "content": "A routing layer directs incoming requests or data
                  to the appropriate destination, service, or
                  processing path."
    },
    "finish_reason": "stop"
  }],
  "usage": { "prompt_tokens": 17, "completion_tokens": 23,
             "total_tokens": 40 }
}