AI Model APIChat
Native Claude Format
Requests in Anthropic Claude Messages API format.
Requires anthropic-version in the request header.
Authorization
BearerAuth
AuthorizationBearer <token>
使用 Bearer Token 认证。
格式: Authorization: Bearer sk-xxxxxx
In: header
Header Parameters
anthropic-version*string
Anthropic API 版本
x-api-key?string
Anthropic API Key (可选，也可使用 Bearer Token)
Request Body
application/json
model*string
messages*array<object>
Array Item (object)
role*string
Value in
"user" | "assistant"content*string | array<object>
Option #1: string
Option #2: array<object>
Array Item (object)
type?string
Value in
"text" | "image" | "tool_use" | "tool_result"text?string
source?object
type?string
Value in
"base64" | "url"media_type?string
data?string
url?string
id?string
name?string
input?object
tool_use_id?string
content?string
system?string | array<object>
Option #1: string
Option #2: array<object>
Array Item (object)
max_tokens*integer
Range
1 <= valuetemperature?number
Range
0 <= value <= 1top_p?number
top_k?integer
stream?boolean
stop_sequences?array<string>
tools?array<object>
Array Item (object)
name?string
description?string
input_schema?object
tool_choice?object
Option #1: object
type?string
Value in
"auto" | "any" | "tool"name?string
thinking?object
type?string
Value in
"enabled" | "disabled"budget_tokens?integer
metadata?object
user_id?string
Response Body
application/json
curl -X POST "https://loading/v1/messages" \ -H "anthropic-version: 2023-06-01" \ -H "Content-Type: application/json" \ -d '{ "model": "claude-3-opus-20240229", "messages": [ { "role": "user", "content": "string" } ], "max_tokens": 1 }'{
"id": "string",
"type": "message",
"role": "assistant",
"content": [
{
"type": "string",
"text": "string"
}
],
"model": "string",
"stop_reason": "end_turn",
"usage": {
"input_tokens": 0,
"output_tokens": 0,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
}How is this guide?
Last updated on