Creare un messaggio
Usa l’API Anthropic Messages tramite CometAPI per chiamare i modelli Claude con adaptive thinking, prompt caching, tool use, web search, streaming e controllo dell’effort.
x-api-key sia Authorization: Bearer sono supportati per l’autenticazione. Gli SDK ufficiali di Anthropic usano x-api-key per impostazione predefinita.Guida rapida
Per usare l’SDK ufficiale di Anthropic con CometAPI, imposta la base URL:Controllare l’adaptive thinking
Usa adaptive thinking conoutput_config.effort per controllare quanto lavoro Claude applica a una risposta. I modelli Claude più recenti rifiutano il formato legacy del thinking manuale thinking={"type": "enabled", "budget_tokens": ...}.
Memorizzare nella cache i prompt
Per ridurre la latenza e il costo nelle richieste successive, memorizza nella cache prompt di sistema di grandi dimensioni o prefissi di conversazione. Aggiungicache_control ai blocchi di contenuto che devono essere memorizzati nella cache:
usage della risposta:
cache_creation_input_tokens— token scritti nella cache (fatturati a una tariffa più alta)cache_read_input_tokens— token letti dalla cache (fatturati a una tariffa ridotta)
Trasmettere le risposte in Streaming
Per trasmettere le risposte in Streaming usando Server-Sent Events (SSE), impostastream: true. Gli eventi arrivano in questo ordine:
message_start— contiene i metadati del messaggio e l’utilizzo inizialecontent_block_start— indica l’inizio di ogni blocco di contenutocontent_block_delta— frammenti di testo incrementali (text_delta)content_block_stop— indica la fine di ogni blocco di contenutomessage_delta—stop_reasonfinale eusagecompletomessage_stop— segnala la fine dello stream
Controllare l’effort
Per controllare quanto impegno Claude mette nella generazione di una risposta, usaoutput_config.effort:
Usare gli strumenti server
Claude supporta strumenti lato server che vengono eseguiti sull’infrastruttura di Anthropic:- Web Fetch
- Web Search
Esempio di risposta
Una risposta tipica dall’endpoint Anthropic di CometAPI:Confronto con l’endpoint compatibile con OpenAI
Autorizzazioni
Your CometAPI key passed via the x-api-key header. Authorization: Bearer $COMETAPI_KEY is also supported.
Intestazioni
The Anthropic API version to use. Defaults to 2023-06-01.
"2023-06-01"
Comma-separated list of beta features to enable. Examples: max-tokens-3-5-sonnet-2024-07-15, pdfs-2024-09-25, output-128k-2025-02-19.
Corpo
The Claude model to use. See the Models page for available Claude model IDs.
"claude-sonnet-5"
The conversation messages. Must alternate between user and assistant roles. Each message's content can be a string or an array of content blocks (text, image, document, tool_use, tool_result). There is a limit of 100,000 messages per request.
The maximum number of tokens to generate. The model may stop before reaching this limit. When using thinking, the thinking tokens count towards this limit.
x >= 11024
System prompt providing context and instructions to Claude. Can be a plain string or an array of content blocks (useful for prompt caching).
Model-dependent sampling control. Many newer Claude models reject non-default temperature values on the Messages API. Omit this field unless you have verified that the selected model accepts it; if the model returns an unsupported or deprecated-parameter error, remove the field instead of substituting another sampling value.
0 <= x <= 11
Model-dependent nucleus sampling control. Many newer Claude models reject non-default top_p values on the Messages API. Omit this field unless you have verified support for the selected model. Do not set temperature and top_p together.
0 <= x <= 11
Model-dependent top-k sampling control. Many newer Claude models reject non-default top_k values on the Messages API. Omit this field unless you have verified support for the selected model.
x >= 00
If true, stream the response incrementally using Server-Sent Events (SSE). Events include message_start, content_block_start, content_block_delta, content_block_stop, message_delta, and message_stop.
Custom strings that cause the model to stop generating when encountered. The stop sequence is not included in the response.
Controls Claude thinking when the selected model supports a configurable thinking mode. For newer adaptive-thinking models, use {"type":"adaptive"} with output_config.effort, or omit thinking when adaptive thinking is already the model default. Manual {"type":"enabled","budget_tokens":...} is supported only by older models and is rejected by newer Claude models.
Tools the model may use. Supports client-defined functions, web search (web_search_20250305), web fetch (web_fetch_20250910), code execution (code_execution_20250522), and more.
Controls how the model uses tools.
Request metadata for tracking and analytics.
Configuration for response effort and output format. Field support depends on the selected Claude model.
The service tier to use. auto tries priority capacity first, standard_only uses only standard capacity.
auto, standard_only Risposta
Successful response. When stream is true, the response is a stream of SSE events.
Unique identifier for this message (e.g., msg_01XFDUDYJgAACzvnptvVoYEL).
Always message.
message Always assistant.
assistant The response content blocks. May include text, thinking, tool_use, and other block types.
The specific model version that generated this response, such as claude-sonnet-5.
Why the model stopped generating. refusal can be returned as a successful HTTP response when the model declines a request.
end_turn, max_tokens, stop_sequence, tool_use, pause_turn, refusal The stop sequence that caused the model to stop, if applicable.
Token usage statistics.