Dreamto AI
登录免费开始

claude-haiku-4-5-kiro-1

claude-haiku-4-5-kiro-1
文本ClaudeCluade-Kiro-1kiro
进入 Playground
Claude Haiku 4.5 是面向高频轻量任务的快速模型，适合日常问答、摘要改写、简单代码辅助、客服回复和结构化信息提取。它的优势是响应快、成本可控，适合需要稳定吞吐和低延迟的业务场景。

鉴权与连接

Base URL
https://backend:8000
Authorization
Authorization: Bearer YOUR_API_KEY
Content-Type
application/json
模型名 (model)
claude-haiku-4-5-kiro-1

接入协议

为什么选这个协议

适合原本使用 Claude SDK 或 Anthropic Messages API 的用户直接迁移。

接口地址
POST/v1/messages
Authorization: Bearer YOUR_API_KEYContent-Type: application/jsonanthropic-version: 2023-06-01

请求 / 响应 JSON

// REQUEST
{
  "model": "claude-haiku-4-5-kiro-1",
  "max_tokens": 4096,
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "你好，世界"
        }
      ]
    }
  ]
}
// RESPONSE
{
  "id": "msg_example",
  "type": "message",
  "role": "assistant",
  "model": "claude-haiku-4-5-kiro-1",
  "content": [
    {
      "type": "text",
      "text": "你好，世界"
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 8,
    "output_tokens": 16
  }
}

请求字段 / 响应字段

// INPUT SCHEMA
字段类型必填
modelstringY
max_tokensintegerY
messagesarrayY
messages[]objectY
messages[].rolestringY
messages[].contentarrayY
messages[].content[]objectY
messages[].content[].typestringY
messages[].content[].textstringY
// RESPONSE SCHEMA
字段类型必填
idstringN
modelstringN
choices[].message.contentstringN
usage.prompt_tokensintegerN
usage.completion_tokensintegerN
usage.total_tokensintegerN

代码示例

cURLrequest.sh
curl -X POST "https://backend:8000/v1/messages" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
  "model": "claude-haiku-4-5-kiro-1",
  "max_tokens": 4096,
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "你好，世界"
        }
      ]
    }
  ]
}'
为什么选这个协议

适合已有 OpenAI SDK、Chat Completions 代码或统一网关接入的用户。

接口地址
POST/v1/chat/completions
Authorization: Bearer YOUR_API_KEYContent-Type: application/json

请求 / 响应 JSON

// REQUEST
{
  "model": "claude-haiku-4-5-kiro-1",
  "messages": [
    {
      "content": "你好，世界",
      "role": "user"
    }
  ],
  "system_instruction": "请用简洁中文回答。",
  "max_tokens": 4096,
  "temperature": 0.7,
  "top_p": 0.95,
  "top_k": 40,
  "thinking": {
    "budget_tokens": 1024,
    "type": "enabled"
  },
  "tools": [],
  "tool_choice": "auto",
  "stream": false
}
// RESPONSE
{
  "id": "chatcmpl_example",
  "model": "gpt-5.5",
  "choices": [
    {
      "message": {
        "content": "你好，世界"
      }
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 16,
    "total_tokens": 24
  }
}

请求字段 / 响应字段

// INPUT SCHEMA
字段类型必填
messagesarrayY
system_instructionstringN
max_tokensintegerN
temperaturenumberN
top_pnumberN
top_kintegerN
thinkingobjectN
toolsarrayN
tool_choicestringN
streambooleanN
// RESPONSE SCHEMA
字段类型必填
idstringN
modelstringN
choices[].message.contentstringN
usage.prompt_tokensintegerN
usage.completion_tokensintegerN
usage.total_tokensintegerN

代码示例

cURLrequest.sh
curl -X POST "https://backend:8000/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "claude-haiku-4-5-kiro-1",
  "messages": [
    {
      "content": "你好，世界",
      "role": "user"
    }
  ],
  "system_instruction": "请用简洁中文回答。",
  "max_tokens": 4096,
  "temperature": 0.7,
  "top_p": 0.95,
  "top_k": 40,
  "thinking": {
    "budget_tokens": 1024,
    "type": "enabled"
  },
  "tools": [],
  "tool_choice": "auto",
  "stream": false
}'