1---
2version: 2
3interactions:
4- id: 0
5 request:
6 proto: HTTP/1.1
7 proto_major: 1
8 proto_minor: 1
9 content_length: 187
10 host: ""
11 body: '{"messages":[{"content":"You are a helpful assistant","role":"system"},{"content":"Say hi in Portuguese","role":"user"}],"model":"z-ai/glm-4.6","max_tokens":4000,"usage":{"include":true}}'
12 headers:
13 Accept:
14 - application/json
15 Content-Type:
16 - application/json
17 User-Agent:
18 - OpenAI/Go 2.7.1
19 url: https://openrouter.ai/api/v1/chat/completions
20 method: POST
21 response:
22 proto: HTTP/2.0
23 proto_major: 2
24 proto_minor: 0
25 content_length: -1
26 uncompressed: true
27 body: "\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n\n \n{\"id\":\"gen-1773324064-bCxdmtgLzZ9hRfv3kUJn\",\"object\":\"chat.completion\",\"created\":1773324064,\"model\":\"z-ai/glm-4.6\",\"provider\":\"AtlasCloud\",\"system_fingerprint\":null,\"choices\":[{\"index\":0,\"logprobs\":null,\"finish_reason\":\"stop\",\"native_finish_reason\":\"stop\",\"message\":{\"role\":\"assistant\",\"content\":\"Oi!\",\"refusal\":null,\"reasoning\":\"1. **Identify the user's request:** The user wants me to say \\\"hi\\\" in Portuguese.\\n\\n2. **Retrieve knowledge about Portuguese greetings:**\\n * \\\"Olá\\\" is the standard, slightly formal but versatile greeting (equivalent to \\\"Hello\\\").\\n * \\\"Oi\\\" is the informal, common greeting (equivalent to \\\"Hi\\\").\\n * \\\"Oi, tudo bem?\\\" (Hi, how are you?) is also very common.\\n\\n3. **Select the best response:** Since the user specifically asked to \\\"say hi\\\", \\\"Oi\\\" is the most direct translation. However, providing \\\"Olá\\\" as well adds value and covers different contexts.\\n\\n4. **Draft the response:**\\n * Option 1: \\\"Oi!\\\"\\n * Option 2: \\\"Olá!\\\"\\n * Option 3: \\\"Oi! or Olá!\\\"\\n\\n5. **Final Polish:** A simple, direct answer is usually best for this type of query.\\n\\n * \\\"Oi!\\\"\\n\\n (I could also add \\\"Olá\\\" for completeness).\\n\\n6. **Final Output Generation:** \\\"Oi!\\\" or \\\"Olá!\\\" are both correct. I will provide the most common informal one first, or just the standard one. Let's go with \\\"Oi!\\\" as it matches \\\"hi\\\" well, but maybe list both.\\n\\n * *Result:* \\\"Oi!\\\" (or \\\"Olá!\\\")\\n\\n Let's just give the most direct translation.\\n\\n \\\"Oi!\\\"\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"text\":\"1. **Identify the user's request:** The user wants me to say \\\"hi\\\" in Portuguese.\\n\\n2. **Retrieve knowledge about Portuguese greetings:**\\n * \\\"Olá\\\" is the standard, slightly formal but versatile greeting (equivalent to \\\"Hello\\\").\\n * \\\"Oi\\\" is the informal, common greeting (equivalent to \\\"Hi\\\").\\n * \\\"Oi, tudo bem?\\\" (Hi, how are you?) is also very common.\\n\\n3. **Select the best response:** Since the user specifically asked to \\\"say hi\\\", \\\"Oi\\\" is the most direct translation. However, providing \\\"Olá\\\" as well adds value and covers different contexts.\\n\\n4. **Draft the response:**\\n * Option 1: \\\"Oi!\\\"\\n * Option 2: \\\"Olá!\\\"\\n * Option 3: \\\"Oi! or Olá!\\\"\\n\\n5. **Final Polish:** A simple, direct answer is usually best for this type of query.\\n\\n * \\\"Oi!\\\"\\n\\n (I could also add \\\"Olá\\\" for completeness).\\n\\n6. **Final Output Generation:** \\\"Oi!\\\" or \\\"Olá!\\\" are both correct. I will provide the most common informal one first, or just the standard one. Let's go with \\\"Oi!\\\" as it matches \\\"hi\\\" well, but maybe list both.\\n\\n * *Result:* \\\"Oi!\\\" (or \\\"Olá!\\\")\\n\\n Let's just give the most direct translation.\\n\\n \\\"Oi!\\\"\",\"format\":\"unknown\",\"index\":0}]}}],\"usage\":{\"prompt_tokens\":15,\"completion_tokens\":314,\"total_tokens\":329,\"cost\":0.00055296,\"is_byok\":false,\"prompt_tokens_details\":{\"cached_tokens\":4,\"cache_write_tokens\":0,\"audio_tokens\":0,\"video_tokens\":0},\"cost_details\":{\"upstream_inference_cost\":0.00055296,\"upstream_inference_prompt_cost\":0.0000066,\"upstream_inference_completions_cost\":0.00054636},\"completion_tokens_details\":{\"reasoning_tokens\":310,\"image_tokens\":0,\"audio_tokens\":0}}}"
28 headers:
29 Content-Type:
30 - application/json
31 status: 200 OK
32 code: 200
33 duration: 1.620134375s