Authorizations
API key to authorize requests.
Body
Model settings and a structured list of input messages with text and/or image content.
The model that will complete your prompt.
Input messages.
"[{\"role\": \"user\", \"content\": \"Hello, Claude\"}]"
The maximum number of tokens to generate before stopping.
A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role.
An object describing metadata about the request.
Custom text sequences that will cause the model to stop generating.
Whether to incrementally stream the response using server-sent events.
Amount of randomness injected into the response.
Use nucleus sampling.
Only sample from the top K options for each subsequent token.
Response
Message object.
Unique object identifier.
For Messages, this is always "message".
This will always be "assistant".
An array of content blocks, each of which has a type. Currently, only type in responses is "text".
"[{\"type\": \"text\", \"text\": \"Hi, I'm Claude.\"}]"
The model that handled the request.
The reason that the model stopped. In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.
end_turn
, max_tokens
, stop_sequence
This value will be a non-null string if one of your custom stop sequences was generated. Else null.
Billing and rate-limit usage.