Create chat autocomplete (streaming)

POST

/v1/messages

Given a hint, the model will return the completion of one or more predictions, and can also return the probability of the alternative label at each location.

Completed creation based on the provided prompts and parameters

Official documentation: https://docs.anthropic.com/en/api/messages

Request

Header Params

Body Params application/json

Example

{
"model": "claude-sonnet-4-20250514",
"system": "You are an intelligent AI assistant named Xiao Wang",
"messages": [
{
"role": "user",
"content": "Who are you?!"
}
],
"stream": true
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location '/v1/messages' \
--header 'Accept: application/json' \
--header 'x-api-key: {{YOUR_API_KEY}}' \
--header 'Content-Type: application/json' \
--data '{
"model": "claude-sonnet-4-20250514",
"system": "You are an intelligent AI assistant named Xiao Wang",
"messages": [
{
"role": "user",
"content": "Who are you?!"
}
],
"stream": true
}'

Responses

🟢200OK

application/json

Bodyapplication/json

Example

{
"id": "chatcmpl-123",
"object": "chat.completion",
"created": 1677652288,
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "\n\nHello there, how may I assist you today?"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 9,
"completion_tokens": 12,
"total_tokens": 21
}
}

Modified at 2026-09-23 08:28:57

Internet search

web search