메시지

메시지 생성

POST/v1/messages

텍스트 및/또는 이미지 콘텐츠가 포함된 구조화된 입력 메시지 목록을 전송하면 모델이 대화의 다음 메시지를 생성합니다.

메시지의 토큰 수 계산

POST/v1/messages/count_tokens

메시지의 토큰 수를 계산합니다.

Models

BetaAdvisorMessageIterationUsage object{ type: "advisor_message", cache_creation, cache_creation_input_tokens, 4 more }

Token usage for an advisor sub-inference iteration.

BetaAdvisorRedactedResultBlock object{ type: "advisor_redacted_result", encrypted_content, stop_reason }

type: "advisor_redacted_result"

defaultadvisor_redacted_result

encrypted_content: string

Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify.

stop_reason: string or null

The advisor sub-inference's stop reason (same values as the top-level message stop_reason).

BetaAdvisorRedactedResultBlockParam object{ type: "advisor_redacted_result", encrypted_content, stop_reason }

type: "advisor_redacted_result"

encrypted_content: string

Opaque blob produced by a prior response; must be round-tripped verbatim.

stop_reason: optional string or null

BetaAdvisorResultBlock object{ type: "advisor_result", stop_reason, text }

type: "advisor_result"

defaultadvisor_result

stop_reason: string or null

The advisor sub-inference's stop reason (same values as the top-level message stop_reason). max_tokens indicates the advisor's output was truncated at the tool's max_tokens value or the advisor model's policy cap.

text: string

BetaAdvisorResultBlockParam object{ type: "advisor_result", text, stop_reason }

type: "advisor_result"

text: string

stop_reason: optional string or null

BetaAdvisorTool20260301 object{ type: "advisor_20260301", model, name, 7 more }

BetaAdvisorToolResultBlock object{ type: "advisor_tool_result", content, tool_use_id }

BetaAdvisorToolResultBlockParam object{ type: "advisor_tool_result", content, tool_use_id, cache_control }

BetaAdvisorToolResultError object{ type: "advisor_tool_result_error", error_code }

type: "advisor_tool_result_error"

defaultadvisor_tool_result_error

error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more

One of the following:

"max_uses_exceeded"

"prompt_too_long"

"too_many_requests"

"overloaded"

"unavailable"

"execution_time_exceeded"

"model_not_found"

BetaAdvisorToolResultErrorParam object{ type: "advisor_tool_result_error", error_code }

type: "advisor_tool_result_error"

error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more

One of the following:

"max_uses_exceeded"

"prompt_too_long"

"too_many_requests"

"overloaded"

"unavailable"

"execution_time_exceeded"

"model_not_found"

BetaAllThinkingTurns object{ type: "all" }

type: "all"

BetaBase64ImageSource object{ type: "base64", data, media_type }

type: "base64"

data: string

formatbyte

media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

One of the following:

"image/jpeg"

"image/png"

"image/gif"

"image/webp"

BetaBase64PDFSource object{ type: "base64", data, media_type }

type: "base64"

data: string

formatbyte

media_type: "application/pdf"

BetaBashCodeExecutionOutputBlock object{ type: "bash_code_execution_output", file_id }

type: "bash_code_execution_output"

defaultbash_code_execution_output

file_id: string

BetaBashCodeExecutionOutputBlockParam object{ type: "bash_code_execution_output", file_id }

type: "bash_code_execution_output"

file_id: string

BetaBashCodeExecutionResultBlock object{ type: "bash_code_execution_result", content, return_code, 2 more }

type: "bash_code_execution_result"

defaultbash_code_execution_result

content: array of BetaBashCodeExecutionOutputBlock { type: "bash_code_execution_output",