API reference

Headers

Send authentication and attribution headers and read cost headers.

Send Authorization: Bearer sk-pg-v1-.... The API accepts HTTP-Referer, X-OpenRouter-Title, and X-Title for app attribution. Responses include X-Generation-Id and plaingateway only X-PG-Host, X-PG-Cost-USD, and X-PG-Request-Id. X-PG-Host names the serving host, X-PG-Cost-USD is the cost in USD, and X-PG-Request-Id is the generation lookup ID.

Request

http

POST https://plaingateway.com/api/v1/chat/completions
Authorization: Bearer sk-pg-v1-...
Content-Type: application/json

{
  "model": "openai/gpt-5.6-luna",
  "messages": [
    {
      "role": "user",
      "content": "Say hello in five words."
    }
  ],
  "max_tokens": 32
}

Response

http

HTTP/1.1 200
{
  "id": "gen-SCRUBBED-1",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "openai/gpt-5.6-luna",
  "provider": "OpenAI",
  "system_fingerprint": null,
  "service_tier": "default",
  "choices": [
    {
      "index": 0,
      "logprobs": null,
      "finish_reason": "stop",
      "native_finish_reason": "completed",
      "message": {
        "role": "assistant",
        "content": "Hello there, nice to meet!",
        "refusal": null,
        "reasoning": null
      }
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 11,
    "total_tokens": 23,
    "cost": 1.56e-05,
    "is_byok": false,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "cache_write_tokens": 0,
      "audio_tokens": 0,
      "video_tokens": 0
    },
    "cost_details": {
      "upstream_inference_cost": 1.56e-05,
      "upstream_inference_prompt_cost": 2.4e-06,
      "upstream_inference_completions_cost": 1.32e-05
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0,
      "image_tokens": 0,
      "audio_tokens": 0
    }
  }
}