- Message(1)
- POSCreate a Message
POST
POST
https://api.lowcodeapi.com/anthropic/v1/messages
Request Body
Content Type : application/json
xxxxxxxxxx18
1
{2
"model": "claude-3-opus-20240229|claude-3-sonnet-20240229|claude-3-haiku-20240307|claude-2.1|claude-2.0|claude-instant-1.2",3
"messages": [4
{5
"role": "user",6
"content": "Hello, world"7
}8
],9
"max_tokens": 1000,10
"stop_sequences": {},11
"metadata": [],12
"stream": "",13
"system": "",14
"temperature": "",15
"tools": [],16
"top_k": "",17
"top_p": ""18
}Request Parameters
modelstring
The model that will complete your prompt
messagesarray
Input messages
max_tokensnumber
The maximum number of tokens to generate before stopping
stop_sequencesobject
An object describing metadata about the request
metadataarray
Custom text sequences that will cause the model to stop generating
streamboolean
Whether to incrementally stream the response using server-sent events
systemstring
System prompt
temperaturenumber
Amount of randomness injected into the response
toolsarray
Definitions of tools that the model may use
top_knumber
Only sample from the top K options for each subsequent token
top_pnumber
Use nucleus sampling
Overview
Response
API response data will be shown here once the request is completed.
Snippet
curl -X POST \
'https://api.lowcodeapi.com/anthropic/v1/messages' \
-H 'Cache-Control: no-cache' \
-H 'Content-Type: application/json' --data-raw '{
"model": "claude-3-opus-20240229|claude-3-sonnet-20240229|claude-3-haiku-20240307|claude-2.1|claude-2.0|claude-instant-1.2",
"messages": [
{
"role": "user",
"content": "Hello, world"
}
],
"max_tokens": 1000,
"stop_sequences": {},
"metadata": [],
"stream": "",
"system": "",
"temperature": "",
"tools": [],
"top_k": "",
"top_p": ""
}'© 2024LowCodeAPI
Last Updated : 2024-12-16 14:03 +00:00