Claude Messages
API Reference
Claude Messages
POST
Claude Messages
Autorisations
API token from https://platform.acedata.cloud
Corps
application/json
The model that will complete your prompt.
Exemple:
"claude-sonnet-4-6"
Input messages.
The maximum number of tokens to generate before stopping.
Exemple:
1024
Custom text sequences that will cause the model to stop generating.
Whether to incrementally stream the response using server-sent events.
System prompt.
Amount of randomness injected into the response.
Plage requise:
0 <= x <= 1Exemple:
1
How the model should use the provided tools.
Definitions of tools that the model may use.
Only sample from the top K options for each subsequent token.
Use nucleus sampling.
Réponse
OK
Unique object identifier.
Options disponibles:
message Options disponibles:
assistant The model that handled the request.
Options disponibles:
end_turn, max_tokens, stop_sequence, tool_use 
