proxybrowser

capture #107

Request (redacted)

POST /api/v1/chat/completions HTTP/1.1
Host: openrouter.ai
Authorization: <redacted sha256:7b7452fd372a>
Content-Type: application/json
Content-Length: 347
Via: <omitted: stack implementation detail>

{"model":"z-ai/glm-4.6","messages":[{"role":"user","content":"Reply with exactly one short sentence: which model are you, and can you see this over the sensed seam?"},{"role":"assistant","content":"I am a large language model, and yes, I can see this."},{"role":"user","content":"What exactly was my previous question? Quote it."}],"stream":false}

Response (redacted)

HTTP/1.1 200 OK
Date: Mon, 20 Jul 2026 03:03:41 GMT
Content-Type: application/json
Transfer-Encoding: chunked
Connection: keep-alive
Server-Timing: cfEdge;dur=5,cfOrigin;dur=0,cfWorker;dur=840
Access-Control-Allow-Origin: *
X-Generation-Id: gen-1784516620-FszTXtuHKNUlf1sgXn3I
access-control-expose-headers: X-Generation-Id,X-Provider-Name,cf-ray
set-cookie: <redacted sha256:fee899b8bd99>
Permissions-Policy: payment=(self "https://checkout.stripe.com" "https://connect-js.stripe.com" "https://js.stripe.com" "https://*.js.stripe.com" "https://hooks.stripe.com")
Referrer-Policy: no-referrer, strict-origin-when-cross-origin
X-Content-Type-Options: nosniff
Server: cloudflare
CF-RAY: a1debbefcb470c92-EWR

{
  "id": "gen-1784516620-FszTXtuHKNUlf1sgXn3I",
  "object": "chat.completion",
  "created": 1784516620,
  "model": "z-ai/glm-4.6",
  "provider": "AtlasCloud",
  "system_fingerprint": null,
  "service_tier": null,
  "choices": [
    {
      "index": 0,
      "logprobs": null,
      "finish_reason": "stop",
      "native_finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "\n\"which model are you, and can you see this over the sensed seam?\"",
        "refusal": null,
        "reasoning": "1.  **Analyze the user's request:** The user wants me to quote their *exact* previous question.\n\n2.  **Recall the previous turn:** The user's previous message was: \"which model are you, and can you see this over the sensed seam?\"\n\n3.  **Identify the key instruction:** \"Quote it.\" This means I need to reproduce the text verbatim, including capitalization, punctuation, and phrasing. I should not paraphrase, summarize, or add any extra information unless it's necessary for framing the quote (e.g., using quotation marks).\n\n4.  **Formulate the response:**\n    *   The most direct and accurate way to fulfill the request is to put the exact text inside quotation marks.\n    *   The text is: \"which model are you, and can you see this over the sensed seam?\"\n    *   I need to be precise. It starts with a lowercase 'w'. It ends with a question mark. It has the comma after \"are you\". It has the exact phrase \"over the sensed seam\".\n\n5.  **Review the response against the request:**\n    *   Is it a quote? Yes.\n    *   Is it of the *previous* question? Yes.\n    *   Is it *exact*? Yes.\n    *   The response: `\"which model are you, and can you see this over the sensed seam?\"` perfectly matches the request.\n\n6.  **Final check:** Is there any ambiguity? No. The request is simple and direct. The planned response is equally simple and direct. It fulfills the user's command precisely. I will just output the quoted text.",
        "reasoning_details": [
          {
            "type": "reasoning.text",
            "text": "1.  **Analyze the user's request:** The user wants me to quote their *exact* previous question.\n\n2.  **Recall the previous turn:** The user's previous message was: \"which model are you, and can you see this over the sensed seam?\"\n\n3.  **Identify the key instruction:** \"Quote it.\" This means I need to reproduce the text verbatim, including capitalization, punctuation, and phrasing. I should not paraphrase, summarize, or add any extra information unless it's necessary for framing the quote (e.g., using quotation marks).\n\n4.  **Formulate the response:**\n    *   The most direct and accurate way to fulfill the request is to put the exact text inside quotation marks.\n    *   The text is: \"which model are you, and can you see this over the sensed seam?\"\n    *   I need to be precise. It starts with a lowercase 'w'. It ends with a question mark. It has the comma after \"are you\". It has the exact phrase \"over the sensed seam\".\n\n5.  **Review the response against the request:**\n    *   Is it a quote? Yes.\n    *   Is it of the *previous* question? Yes.\n    *   Is it *exact*? Yes.\n    *   The response: `\"which model are you, and can you see this over the sensed seam?\"` perfectly matches the request.\n\n6.  **Final check:** Is there any ambiguity? No. The request is simple and direct. The planned response is equally simple and direct. It fulfills the user's command precisely. I will just output the quoted text.",
            "format": "unknown",
            "index": 0
          }
        ]
      }
    }
  ],
  "usage": {
    "prompt_tokens": 59,
    "completion_tokens": 363,
    "total_tokens": 422,
    "cost": 0.000834,
    "is_byok": false,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "cache_write_tokens": 0,
      "audio_tokens": 0,
      "video_tokens": 0
    },
    "cost_details": {
      "upstream_inference_cost": 0.000834,
      "upstream_inference_prompt_cost": 3.54e-5,
      "upstream_inference_completions_cost": 0.0007986
    },
    "completion_tokens_details": {
      "reasoning_tokens": 343,
      "image_tokens": 0,
      "audio_tokens": 0
    }
  }
}