Criar uma Message
Use a API Anthropic Messages por meio do CometAPI para chamar modelos Claude com adaptive thinking, prompt caching, uso de ferramentas, pesquisa na web, streaming e controle de effort.
x-api-key quanto Authorization: Bearer são suportados para autenticação. Os SDKs oficiais da Anthropic usam x-api-key por padrão.Início rápido
Para usar o SDK oficial da Anthropic com o CometAPI, defina a URL base:Controlar adaptive thinking
Use adaptive thinking comoutput_config.effort para controlar quanto trabalho o Claude aplica a uma resposta. Modelos Claude mais recentes rejeitam o formato manual legado de thinking thinking={"type": "enabled", "budget_tokens": ...}.
Cache prompts
Para reduzir a latência e o custo em solicitações subsequentes, coloque em cache grandes prompts de sistema ou prefixos de conversa. Adicionecache_control aos blocos de content que devem ser armazenados em cache:
usage da resposta:
cache_creation_input_tokens— Tokens gravados no cache (cobrados a uma taxa mais alta)cache_read_input_tokens— Tokens lidos do cache (cobrados a uma taxa reduzida)
Stream responses
Para fazer Streaming de respostas usando Server-Sent Events (SSE), definastream: true. Os eventos chegam nesta ordem:
message_start— contém os metadados da mensagem e o uso inicialcontent_block_start— marca o início de cada bloco de contentcontent_block_delta— partes incrementais de texto (text_delta)content_block_stop— marca o fim de cada bloco de contentmessage_delta—stop_reasonfinal eusagecompletomessage_stop— sinaliza o fim do stream
Control effort
Para controlar quanto esforço Claude dedica à geração de uma resposta, useoutput_config.effort:
Use server tools
Claude oferece suporte a ferramentas do lado do servidor que são executadas na infraestrutura da Anthropic:- Web Fetch
- Web Search
Response example
Um exemplo típico de resposta do endpoint Anthropic da CometAPI:Comparar com o endpoint compatível com OpenAI
Autorizações
Your CometAPI key passed via the x-api-key header. Authorization: Bearer $COMETAPI_KEY is also supported.
Cabeçalhos
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 Resposta
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.