Three products, one loop.

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 }
}

Already on the Messages API? Same gateway, no migration.

POST /v1/messages

{
  "model": "anthropic/claude-sonnet-5",
  "max_tokens": 120,
  "messages": [
    { "role": "user",
      "content": "In one sentence: what does a routing layer do?" }
  ]
}

{
  "type": "message",
  "role": "assistant",
  "model": "anthropic/claude-sonnet-5",
  "content": [{
    "type": "text",
    "text": "A routing layer examines incoming requests and directs
             them to the appropriate destination — a service,
             handler, server, or processing path — based on
             defined rules, criteria, or logic."
  }],
  "stop_reason": "end_turn",
  "usage": { "input_tokens": 21, "output_tokens": 63 }
}

Every call is quoted before it runs, so a budget can be enforced by the caller — not reconciled weeks later.

POST /v1/chat/completions

{
  "model": "anthropic/claude-opus-5",
  "messages": [
    { "role": "user",
      "content": "Summarise this 40-page contract." }
  ],
  "max_tokens": 4096
}

HTTP/1.1 402 Payment Required

{
  "amount_usd": 0.01141,
  "for": "Claude Opus 5 API call
          (~32 input, 4096 max output tokens)",
  "maxTimeoutSeconds": 300
}

# The price arrives before the work does. Your client decides
# whether to pay it — an over-budget call is never made, so
# there is nothing to claw back.

Which agent spent what, on which model, is a query — not an investigation at the end of the month.

GET /v1/wallet/{address}/reconciliation?days=7

# No key, no dashboard login. The field is named revenueUsd
# because it is the same number on both sides of the invoice.

{
  "days": 7,
  "totals": {
    "calls": 47,
    "inputTokens": 1467,
    "outputTokens": 6227,
    "revenueUsd": 0.37435508
  },
  "perModel": [
    { "model": "deepseek/deepseek-chat",
      "calls": 15, "inputTokens": 106,
      "outputTokens": 59, "revenueUsd": 0.00102744 },
    { "model": "deepseek/deepseek-v4-pro",
      "calls": 14, "inputTokens": 1246,
      "outputTokens": 140, "revenueUsd": 0.00066381 },
    { "model": "anthropic/claude-opus-5",
      "calls": 1, "inputTokens": 16,
      "outputTokens": 4, "revenueUsd": 0.001 }
  ],
  "services": [
    { "service": "chat",  "calls": 46, "revenueUsd": 0.02043935 },
    { "service": "video", "calls": 1,  "revenueUsd": 0.35391573 }
  ]
}