llama-stack-mirror/tests/integration/recordings/responses/a1c5bf09ea53.json
Matthew Farrellee 1f7e87c647 feat: update Cerebras inference provider to support dynamic model listing
- update Cerebras to use OpenAIMixin
- enable openai completions tests
- enable openai chat completions tests
- disable with n > 1 tests
- add recording for --setup cerebras --subdirs inference --pattern openai

test with: `./scripts/integration-tests.sh --stack-config server:ci-tests --setup cerebras --subdirs inference --pattern openai`
2025-09-18 06:54:05 -04:00

66 lines
1.8 KiB
JSON

{
"request": {
"method": "POST",
"url": "https://api.cerebras.ai/v1/v1/chat/completions",
"headers": {},
"body": {
"model": "llama-3.3-70b",
"messages": [
{
"role": "user",
"content": "Hello, world!"
}
],
"stream": false
},
"endpoint": "/v1/chat/completions",
"model": "llama-3.3-70b"
},
"response": {
"body": {
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
"__data__": {
"id": "chatcmpl-1dcfef1f-f955-4158-a1fc-0c2643b60e4e",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "Hello! It's nice to meet you. Is there something I can help you with or would you like to chat?",
"refusal": null,
"role": "assistant",
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": null
}
}
],
"created": 1758191362,
"model": "llama-3.3-70b",
"object": "chat.completion",
"service_tier": null,
"system_fingerprint": "fp_c5ec625e72d41732d8fd",
"usage": {
"completion_tokens": 25,
"prompt_tokens": 39,
"total_tokens": 64,
"completion_tokens_details": null,
"prompt_tokens_details": {
"audio_tokens": null,
"cached_tokens": 0
}
},
"time_info": {
"queue_time": 0.083508803,
"prompt_time": 0.003352167,
"completion_time": 0.011506416,
"total_time": 0.09965348243713379,
"created": 1758191362
}
}
},
"is_streaming": false
}
}