跳转到主要内容

​
Claude PDF 支持

Claude 模型支持直接处理 PDF 文档。你可以通过 URL 或 Base64 编码发送 PDF 文件，让 Claude 阅读、分析和总结文档内容。 
POST /v1/messages

​
通过 URL 发送 PDF

curl https://crazyrouter.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "max_tokens": 4096,
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "document",
            "source": {
              "type": "url",
              "url": "https://example.com/report.pdf"
            }
          },
          {
            "type": "text",
            "text": "总结这份文档的主要内容，列出关键要点"
          }
        ]
      }
    ]
  }'

​
通过 Base64 发送 PDF

curl https://crazyrouter.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "max_tokens": 4096,
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "document",
            "source": {
              "type": "base64",
              "media_type": "application/pdf",
              "data": "JVBERi0xLjQKMSAwIG9iago..."
            }
          },
          {
            "type": "text",
            "text": "这份合同的主要条款有哪些？"
          }
        ]
      }
    ]
  }'

​
多文档分析

可以同时发送多个 PDF 进行对比分析：
Python
message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=4096,
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document",
                    "source": {
                        "type": "url",
                        "url": "https://example.com/report_q1.pdf"
                    }
                },
                {
                    "type": "document",
                    "source": {
                        "type": "url",
                        "url": "https://example.com/report_q2.pdf"
                    }
                },
                {
                    "type": "text",
                    "text": "对比这两份季度报告，分析关键指标的变化趋势"
                }
            ]
        }
    ]
)

​
流式处理

PDF 分析也支持流式输出：
Python
with client.messages.stream(
    model="claude-sonnet-4-20250514",
    max_tokens=4096,
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "document",
                    "source": {"type": "url", "url": "https://example.com/paper.pdf"}
                },
                {"type": "text", "text": "详细分析这篇论文的研究方法和结论"}
            ]
        }
    ]
) as stream:
    for text in stream.text_stream:
        print(text, end="")
PDF 文档的每一页都会消耗 Token。页数越多，消耗越大。建议对大型文档进行分页处理或提取关键页面。
PDF 文件大小建议不超过 32MB。过大的文件可能导致请求超时。