deepseek怎么判断是不是满血或者max思考呢，闲鱼现在挺多第三方ds的，怎么可以判断也没有掺水还是ds2api的
GLM我有，但是太卡了，只能在非高峰期用
看响应请求都是差不多的（不是很懂喵）
这个是第三方的
{
"id": "d2f27541-15a2-4d54-a261-556e0d44f1e8",
"model": "deepseek-v4-pro",
"usage": {
"total_tokens": 183290,
"prompt_tokens": 182814,
"completion_tokens": 476,
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 181760
},
"completion_tokens_details": {
"audio_tokens": 0,
"reasoning_tokens": 100,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
},
"object": "chat.completion",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_00_PfB6XlNp3vl5Dj0yUFJe0367",
"type": "function",
"index": 0,
"function": {
"name": "PatchEdit",
"arguments": {}
}
},
"reasoning_content": ""
},
"finish_reason": "tool_calls"
}
],
"created": 1779010506,
"system_fingerprint": "fp_9954b31ca7_prod0820_fp8_kvcache_20260402"
}
这个是官方的：
{
"id": "91904a7b-5ea2-4fcb-b404-be710ed48189",
"model": "deepseek-v4-pro",
"usage": {
"total_tokens": 151,
"prompt_tokens": 26,
"completion_tokens": 125,
"prompt_tokens_details": {
"cached_tokens": 0
},
"prompt_cache_hit_tokens": 0,
"prompt_cache_miss_tokens": 26,
"completion_tokens_details": {
"reasoning_tokens": 65
}
},
"object": "chat.completion",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "",
"reasoning_content": ""
},
"logprobs": null,
"finish_reason": "stop"
}
],
"created": 1779010651,
"system_fingerprint": "fp_9954b31ca7_prod0820_fp8_kvcache_20260402"
}
22 个帖子 - 10 位参与者
来源: LinuxDo 最新话题查看原文