apinebula.ai

响应字段与官方 Messages API 规范一致

{
  "status": 200,
  "id": "msg_018coKiehsP1q6NNMOWSQH1J",
  "model": "claude-sonnet-5",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 40,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0,
    "cache_creation": {
      "ephemeral_5m_input_tokens": 0,
      "ephemeral_1h_input_tokens": 0
    },
    "output_tokens": 4,
    "service_tier": "standard",
    "inference_geo": "not_available",
    "output_tokens_details": {
      "thinking_tokens": 0
    }
  },
  "topKeys": [
    "model",
    "id",
    "type",
    "role",
    "content",
    "stop_reason",
    "stop_sequence",
    "stop_details",
    "usage"
  ],
  "latencyMs": 3613,
  "text": "OK"
}

消息 ID 符合官方格式且每次唯一

{
  "ids": [
    "msg_018coKiehsP1q6NNMOWSQH1J",
    "msg_01wbzbL68k0gcubJsCgvOZiO"
  ]
}

开启 thinking 后请求失败 (HTTP 400)：<nil>: "***.***.enabled" is not supported for this model. Use "***.***.adaptive" and "output_config.effort" to control thinking behavior. (request_ori_id: 582fd615-6811-425c-a4fb-bb506bb36b60) (request id: 202608291017423843233338268d9d6TeY9883M) (request id: 202608291017422927227598268d9d6pbonvEeT)

{
  "status": 400,
  "body": "{\"error\":{\"type\":\"\\u003cnil\\u003e\",\"message\":\"\\\"***.***.enabled\\\" is not supported for this model. Use \\\"***.***.adaptive\\\" and \\\"output_config.effort\\\" to control thinking behavior. (request_ori_id: 582fd615-6811-425c-a4fb-bb506bb36b60) (request id: 202608291017423843233338268d9d6TeY9883M) (request id: 202608291017422927227598268d9d6pbonvEeT)\"},\"type\":\"error\"}"
}

SSE 事件序列完整，符合官方规范

{
  "status": 200,
  "ttftMs": 1271,
  "eventCount": 11,
  "sequence": [
    "message_start",
    "content_block_start",
    "ping",
    "content_block_delta",
    "content_block_delta",
    "content_block_stop",
    "content_block_start",
    "content_block_delta",
    "content_block_stop",
    "message_delta",
    "message_stop"
  ],
  "startId": "msg_01UkDbgOjUYOPCSGqLKYwbVS",
  "startUsage": {
    "input_tokens": 46,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0,
    "cache_creation": {
      "ephemeral_5m_input_tokens": 0,
      "ephemeral_1h_input_tokens": 0
    },
    "output_tokens": 2,
    "service_tier": "standard",
    "inference_geo": "not_available"
  },
  "deltaUsage": {
    "input_tokens": 46,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0,
    "output_tokens": 31,
    "output_tokens_details": {
      "thinking_tokens": 16
    }
  }
}

Tool Use 正常，参数与 stop_reason 均符合规范

{
  "stop_reason": "tool_use",
  "blockTypes": [
    "tool_use"
  ],
  "toolId": "toolu_017SFGbjDVxwP2jUJvCjmYAN",
  "input": {
    "command": "echo tokyo"
  }
}

预填充请求失败 HTTP 400：<nil>: This model does not support assistant message prefill. The conversation must end with a user message. (request_ori_id: 5282b3db-546a-419e-ba45-85375198837b) (request id: 202608291017486338872598268d9d6JvTrPjSR) (request id: 202608291017485334744198268d9d6BQtYQbnj)

{
  "status": 400
}

stop_sequences 未生效：输出中仍包含停止词，参数未透传

{
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "text": "ONE TWO THREE FOUR FIVE SIX"
}

用量稳定 (40 tokens)，无注入痕迹

{
  "input_tokens": [
    40,
    40
  ],
  "output_tokens": [
    4,
    4
  ],
  "expectedInputApprox": "10-16"
}

除我们发送的 Claude Code 前缀外无其他隐藏指令

{
  "reply": "NONE",
  "extra": ""
}

身份为 Anthropic，temperature=0 输出稳定

{
  "who": "Anthropic",
  "math": [
    "391",
    "391"
  ],
  "models": [
    "claude-sonnet-5",
    "claude-sonnet-5",
    "claude-sonnet-5"
  ]
}

PDF 内容识别正确

{
  "status": 200,
  "secret": "KIWI-8941",
  "reply": "KIWI-8941"
}

缓存写入 7513 tokens、第二次命中 7513 tokens，Prompt Caching 完整可用

{
  "first": {
    "input": 14,
    "creation": 7513,
    "read": 0
  },
  "second": {
    "input": 14,
    "creation": 0,
    "read": 7513
  }
}

100k 通过，190k 失败：宣称上下文与实际不符

{
  "tiers": [
    {
      "tokens": 32000,
      "ok": true,
      "status": 200,
      "latencyMs": 4321,
      "inputTokens": 47818,
      "reply": "191380"
    },
    {
      "tokens": 100000,
      "ok": true,
      "status": 200,
      "latencyMs": 5929,
      "inputTokens": 149255,
      "reply": "643811"
    },
    {
      "tokens": 190000,
      "ok": false,
      "status": 200,
      "latencyMs": 5921,
      "inputTokens": 283503,
      "reply": ""
    }
  ]
}