Claude 聊天
POST
/v1/messages
需要在请求头中包含
anthropic-version。文件分析（多模态文件输入）
messages。图片用 image 块，PDF/文档用 document 块。文件来源三选一：base64、url、或 Files API 上传后的 file（file_id）。兼容性： base64最通用最稳；url由网关向源站拉取，部分逆向上游可能不支持外链，优先用 base64；file_id需先调用 Files 上传接口拿到 ID，并在请求头加anthropic-beta: files-api-2025-04-14。
图片（base64）
{
"model": "claude-sonnet-4-5",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": [
{ "type": "image", "source": { "type": "base64", "media_type": "image/png", "data": "<BASE64_无前缀>" } },
{ "type": "text", "text": "请描述这张图片" }
]
}
]
}图片（URL）
{
"model": "claude-sonnet-4-5",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": [
{ "type": "image", "source": { "type": "url", "url": "https://example.com/a.png" } },
{ "type": "text", "text": "请描述这张图片" }
]
}
]
}PDF / 文档（base64）
{
"model": "claude-sonnet-4-5",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": [
{ "type": "document", "source": { "type": "base64", "media_type": "application/pdf", "data": "<BASE64_无前缀>" } },
{ "type": "text", "text": "总结这份文档的要点" }
]
}
]
}PDF / 文档（URL）
{
"model": "claude-sonnet-4-5",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": [
{ "type": "document", "source": { "type": "url", "url": "https://example.com/a.pdf" } },
{ "type": "text", "text": "总结这份文档的要点" }
]
}
]
}PDF / 文档（Files API 文件引用）
{
"model": "claude-sonnet-4-5",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": [
{ "type": "document", "source": { "type": "file", "file_id": "file_xxx" } },
{ "type": "text", "text": "总结这份文档的要点" }
]
}
]
}media_type 需与实际文件一致。请求参数
Header 参数
Body 参数application/json
返回响应
请求示例请求示例
Shell
JavaScript
Java
Swift
curl --location 'https://api.openai-hub.net/v1/messages' \
--header 'anthropic-version;' \
--header 'x-api-key;' \
--header 'Authorization: Bearer sk-0ABIEXVjh9****Qckjy' \
--header 'Content-Type: application/json' \
--data '{
"model": "claude-3-opus-20240229",
"messages": [
{
"role": "user",
"content": "string"
}
],
"system": "string",
"cache_control": {},
"inference_geo": "string",
"max_tokens": 1,
"temperature": 0,
"top_p": 0,
"top_k": 0,
"stream": true,
"stop_sequences": [
"string"
],
"tools": [
{
"name": "string",
"description": "string",
"input_schema": {}
}
],
"tool_choice": {
"type": "auto",
"name": "string"
},
"thinking": {
"type": "enabled",
"budget_tokens": 0
},
"context_management": {},
"output_config": {},
"output_format": {},
"container": "string",
"mcp_servers": [
{}
],
"metadata": {
"user_id": "string"
},
"speed": "standard",
"service_tier": "auto"
}'响应示例响应示例
{
"content": [
{
"text": "Hey there! 👋 How's it going? What are you working on today?",
"type": "text"
}
],
"id": "msg_ca3e4f862a4040739b7c38a5f0e92d5e",
"model": "claude-opus-4.7",
"role": "assistant",
"stop_reason": "end_turn",
"stop_sequence": null,
"type": "message",
"usage": {
"cache_creation": {
"ephemeral_1h_input_tokens": 0,
"ephemeral_5m_input_tokens": 0
},
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
"input_tokens": 4,
"output_tokens": 23
}
}