Skip to main content
POST
/
v1
/
messages
curl -X POST https://qingbo.dev/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-5-20250929",
    "max_tokens": 1024,
    "system": "你是一个专业的AI助手。",
    "messages": [
      {
        "role": "user",
        "content": "解释一下冒泡排序算法。"
      }
    ]
  }'

{
  "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF",
"type": "message",
"role": "assistant",
"content": [
  {
    "type": "text",
      "text": "你好！我是Claude。很高兴见到你。"
  }
],
  "model": "claude-sonnet-4-5-20250929",
"stop_reason": "end_turn",
  "stop_sequence": null,
"usage": {
    "input_tokens": 12,
    "output_tokens": 18
}
}
  • Fully compatible with the Claude Messages API format
  • Supports multi-turn conversations and single queries
  • Supports text, images, and other multimodal content
curl -X POST https://qingbo.dev/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-5-20250929",
    "max_tokens": 1024,
    "system": "你是一个专业的AI助手。",
    "messages": [
      {
        "role": "user",
        "content": "解释一下冒泡排序算法。"
      }
    ]
  }'

{
  "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF",
"type": "message",
"role": "assistant",
"content": [
  {
    "type": "text",
      "text": "你好！我是Claude。很高兴见到你。"
  }
],
  "model": "claude-sonnet-4-5-20250929",
"stop_reason": "end_turn",
  "stop_sequence": null,
"usage": {
    "input_tokens": 12,
    "output_tokens": 18
}
}

​
Authorizations

​
x-api-key
string
required
API key for authenticationVisit the API Key management page to get your API KeyAdd the following to your request headers:
x-api-key: YOUR_API_KEY
​
anthropic-version
string
required
API versionSpecifies the Claude API version to useExample: 2023-06-01

​
Body

​
model
string
required
Model name
  • claude-haiku-4-5-20251001 - Claude 4.5 fast response version
  • claude-sonnet-4-5-20250929 - Claude 4.5 balanced version
  • claude-opus-4-1-20250805 - Most powerful Claude 4.1 flagship model
  • claude-opus-4-1-20250805-thinking - Claude 4.1 Opus deep thinking version
  • claude-sonnet-4-5-20250929-thinking - Claude 4.5 Sonnet deep thinking version
​
messages
array
required
Message list, supports alternating user and assistant roles
​
max_tokens
integer
required
Maximum tokens to generateThe maximum number of tokens before generation stops. The model may stop before reaching this limit.Different models have different maximums. Refer to the model documentation.Minimum: 1
​
system
string | array
System promptThe system prompt sets Claude’s role, personality, goals, and instructions.String format:
{
  "system": "你是一位专业的Python编程导师"
}
Structured format:
{
  "system": 
  [
    {
      "type": "text",
      "text": "你是一位专业的Python编程导师"
    }
  ]
}
​
temperature
number
Temperature parameter, range 0-1Controls output randomness:
  • Low values (e.g., 0.2): More deterministic, more conservative
  • High values (e.g., 0.8): More random, more creative
Default: 1.0
​
top_p
number
Nucleus sampling parameter, range 0-1Uses nucleus sampling. It is recommended to use either temperature or top_p, not both.Default: 1.0
​
top_k
integer
Top-K samplingSamples only from the top K most probable options, removing “long tail” low-probability responses.Recommended for advanced use cases only.
​
stream
boolean
Whether to enable streaming output
  • true: Stream responses progressively via Server-Sent Events (SSE)
  • false: Return the complete response at once
Default: false
​
stop_sequences
array
Stop sequencesCustom text sequences that stop generation when encountered. Up to 4 sequences, each up to 32 tokens.
​
metadata
object
MetadataAn object for tracking or identifying requests.

​
Response

​
id
string
Unique identifier for the message
​
type
string
Object type, always message
​
role
string
Role type, always assistant
​
content
array
Message content array
​
model
string
The model name actually used
​
stop_reason
string
Stop reasonPossible values:
  • end_turn - Natural completion
  • max_tokens - Maximum token limit reached
  • stop_sequence - Stop sequence encountered
  • tool_use - Tool use
​
stop_sequence
string
The stop sequence that triggered the stop (if applicable)
​
usage
object
Token usage statistics

​
Usage Examples

​
Single Conversation

{
  "model": "claude-sonnet-4-5-20250929",
  "max_tokens": 1024,
  "messages": [
    {"role": "user", "content": "解释一下量子计算"}
  ]
}

​
Multi-Turn Conversation

{
  "model": "claude-sonnet-4-5-20250929",
  "max_tokens": 1024,
  "messages": [
    {"role": "user", "content": "你好"},
    {"role": "assistant", "content": "你好！我是Claude。"},
    {"role": "user", "content": "能解释一下AI吗？"}
  ]
}

​
Using a System Prompt

{
  "model": "claude-sonnet-4-5-20250929",
  "max_tokens": 1024,
  "system": "你是一位经验丰富的数据科学家，专长包括统计分析和机器学习。",
  "messages": [
    {"role": "user", "content": "如何选择合适的机器学习算法？"}
  ]
}

​
Prefilling the Response

{
  "model": "claude-sonnet-4-5-20250929",
  "max_tokens": 1024,
  "messages": [
    {"role": "user", "content": "列出5个Python最佳实践"},
    {"role": "assistant", "content": "以下是5个Python最佳实践：\n\n1."}
  ]
}