Create message

Send a message to an Anthropic-compatible model and receive a response

x-api-keystring required

Your Requesty API key

anthropic-versionstring

Example:2023-06-01

The version of the Anthropic API to use

Request body

modelstring required

The model to use for the completion

max_tokensinteger required

The maximum number of tokens to generate before stopping

systemstring

System prompt to be used for the completion

temperaturenumber

Amount of randomness injected into the response

top_pnumber

Use nucleus sampling

top_kinteger

Only sample from the top K options for each subsequent token

streamboolean

Whether to incrementally stream the response using server-sent events

stop_sequencesstring[]

Custom text sequences that will cause the model to stop generating

{
  "model": "anthropic/claude-sonnet-4-20250514",
  "max_tokens": 1024
}

Message response

idstring required

Unique object identifier

type'message' required

Object type

role'assistant' required

Conversational role of the generated message

modelstring required

The model that handled the request

stop_reason'end_turn' | 'max_tokens' | 'stop_sequence' | 'tool_use' required

The reason that we stopped

stop_sequencestring

Which custom stop sequence was generated