Ergebnisse eines Message Batch abrufen

$ ant beta:messages:batches results

GET/v1/messages/batches/{message_batch_id}/results

Streamt die Ergebnisse eines Message Batch als .jsonl-Datei.

Jede Zeile der Datei ist ein JSON-Objekt, das das Ergebnis einer einzelnen Anfrage im Message Batch enthält. Es ist nicht garantiert, dass die Ergebnisse in derselben Reihenfolge wie die Anfragen vorliegen. Verwende das Feld custom_id, um Ergebnisse den Anfragen zuzuordnen.

Mehr über die Message Batches API erfährst du in unserem Benutzerhandbuch

Parameters

--message-batch-id: string

ID of the Message Batch.

--beta: optional array of AnthropicBeta

Optional header to specify the beta version(s) you want to use.

Returns

beta_message_batch_individual_response: object{ custom_id, result }

This is a single line in the response .jsonl file and does not represent the response as a whole.

custom_id: string

Developer-provided ID created for each request in a Message Batch. Useful for matching results to requests, as results may be given out of request order.

Must be unique for each request within the Message Batch.

result: BetaMessageBatchSucceededResult { message, type } or BetaMessageBatchErroredResult { error, type } or BetaMessageBatchCanceledResult { type } or BetaMessageBatchExpiredResult { type }

Processing result for this request.

Contains a Message output if processing was successful, an error response if processing failed, or the reason why processing was not attempted, such as cancellation or expiration.

One of the following:

beta_message_batch_succeeded_result: object{ message, type }

message: object{ id, container, content, 10 more }

id: string

Unique object identifier.

The format and length of IDs may change over time.

container: object{ id, expires_at, skills }

Information about the container used in the request (for the code execution tool)

id: string

Identifier for the container used in this request

expires_at: string

The time at which the container will expire.

formatdate-time

skills: array of BetaContainerSkill { skill_id, type, version }

Skills loaded in the container

skill_id: string

Skill ID

maxLength64

minLength1

type: "anthropic" or "custom"

Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)

One of the following:

"anthropic"

"custom"

version: string

The resolved version: a skill version ID for custom skills.

maxLength64

minLength1

content: array of BetaContentBlock

Content generated by the model.

This is an array of content blocks, each of which has a type that determines its shape.

Example:

[{"type": "text", "text": "Hi, I'm Claude."}]

If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.

For example, if the input messages were:

[
  {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
  {"role": "assistant", "content": "The best answer is ("}
]

Then the response content might be:

[{"type": "text", "text": "B)"}]

One of the following:

beta_text_block: object{ citations, text, type }

citations: array of BetaTextCitation

Citations supporting the text block.

The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.

One of the following:

beta_citation_char_location: object{ cited_text, document_index, document_title, 4 more }

cited_text: string

document_index: number

minimum0

document_title: string

end_char_index: number

file_id: string

start_char_index: number

minimum0

type: "char_location"

beta_citation_page_location: object{ cited_text, document_index, document_title, 4 more }

cited_text: string

document_index: number

minimum0

document_title: string

end_page_number: number

file_id: string

start_page_number: number

minimum1

type: "page_location"

beta_citation_content_block_location: object{ cited_text, document_index, document_title, 4 more }

cited_text: string

The full text of the cited block range, concatenated.

Always equals the contents of content[start_block_index:end_block_index] joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns.

document_index: number

minimum0

document_title: string

end_block_index: number

Exclusive 0-based end index of the cited block range in the source's content array.

Always greater than start_block_index; a single-block citation has end_block_index = start_block_index + 1.

file_id: string

start_block_index: number

0-based index of the first cited block in the source's content array.

minimum0

type: "content_block_location"

beta_citations_web_search_result_location: object{ cited_text, encrypted_index, title, 2 more }

cited_text: string

encrypted_index: string

title: string

maxLength512

type: "web_search_result_location"

url: string

beta_citation_search_result_location: object{ cited_text, end_block_index, search_result_index, 4 more }

cited_text: string

The full text of the cited block range, concatenated.

end_block_index: number

Exclusive 0-based end index of the cited block range in the source's content array.

Always greater than start_block_index; a single-block citation has end_block_index = start_block_index + 1.

search_result_index: number

0-based index of the cited search result among all search_result content blocks in the request, in the order they appear across messages and tool results.

Counted separately from document_index; server-side web search results are not included in this count.

minimum0

source: string

start_block_index: number

0-based index of the first cited block in the source's content array.

minimum0

title: string

type: "search_result_location"

text: string

maxLength5000000

minLength0

type: "text"

beta_thinking_block: object{ signature, thinking, type }

signature: string

A value used to verify that this thinking block was generated by Claude when it is passed back to the API.

This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact.

See extended thinking for details.

thinking: string

The text of Claude's thinking process for this block.

type: "thinking"

beta_redacted_thinking_block: object{ data, type }

data: string

The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content.

Pass redacted_thinking blocks back to the API unchanged when continuing a multi-turn conversation.

See extended thinking for details.

type: "redacted_thinking"

beta_tool_use_block: object{ id, input, name, 3 more }

id: string

pattern^[a-zA-Z0-9_-]+$

input: map[unknown]

minLength1

type: "tool_use"

caller: optional BetaDirectCaller { type } or BetaServerToolCaller { tool_id, type } or BetaServerToolCaller20260120 { tool_id, type }

Tool invocation directly from the model.

One of the following:

beta_direct_caller: object{ type }

Tool invocation directly from the model.

type: "direct"

beta_server_tool_caller: object{ tool_id, type }

Tool invocation generated by a server-side tool.

tool_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "code_execution_20250825"

beta_server_tool_caller_20260120: object{ tool_id, type }

tool_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "code_execution_20260120"

toolset_name: optional string

For a toolset member tool_use, the toolset family.

maxLength64

minLength1

pattern^[a-zA-Z0-9_-]+$

beta_server_tool_use_block: object{ id, input, name, 2 more }

id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

input: map[unknown]

One of the following:

"advisor"

"web_search"

"web_fetch"

"code_execution"

"bash_code_execution"

"text_editor_code_execution"

"tool_search_tool_regex"

"tool_search_tool_bm25"

type: "server_tool_use"

caller: optional BetaDirectCaller { type } or BetaServerToolCaller { tool_id, type } or BetaServerToolCaller20260120 { tool_id, type }

Tool invocation directly from the model.

One of the following:

beta_direct_caller: object{ type }

Tool invocation directly from the model.

type: "direct"

beta_server_tool_caller: object{ tool_id, type }

Tool invocation generated by a server-side tool.

tool_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "code_execution_20250825"

beta_server_tool_caller_20260120: object{ tool_id, type }

tool_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "code_execution_20260120"

beta_web_search_tool_result_block: object{ content, tool_use_id, type, caller }

content: BetaWebSearchToolResultError { error_code, type } or array of BetaWebSearchResultBlock { encrypted_content, page_age, title, 2 more }

One of the following:

beta_web_search_tool_result_error: object{ error_code, type }

error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more

One of the following:

"invalid_tool_input"

"unavailable"

"max_uses_exceeded"

"too_many_requests"

"query_too_long"

"request_too_large"

type: "web_search_tool_result_error"

union_member_1: array of BetaWebSearchResultBlock { encrypted_content, page_age, title, 2 more }

encrypted_content: string

page_age: string

title: string

type: "web_search_result"

url: string

tool_use_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "web_search_tool_result"

caller: optional BetaDirectCaller { type } or BetaServerToolCaller { tool_id, type } or BetaServerToolCaller20260120 { tool_id, type }

Tool invocation directly from the model.

One of the following:

beta_direct_caller: object{ type }

Tool invocation directly from the model.

type: "direct"

beta_server_tool_caller: object{ tool_id, type }

Tool invocation generated by a server-side tool.

tool_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "code_execution_20250825"

beta_server_tool_caller_20260120: object{ tool_id, type }

tool_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "code_execution_20260120"

beta_web_fetch_tool_result_block: object{ content, tool_use_id, type, caller }

content: BetaWebFetchToolResultErrorBlock { error_code, type } or BetaWebFetchBlock { content, retrieved_at, type, url }

One of the following:

beta_web_fetch_tool_result_error_block: object{ error_code, type }

error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 6 more

One of the following:

"invalid_tool_input"

"url_too_long"

"url_not_allowed"

"url_not_in_prior_context"

"url_not_accessible"

"unsupported_content_type"

"too_many_requests"

"max_uses_exceeded"

"unavailable"

type: "web_fetch_tool_result_error"

beta_web_fetch_block: object{ content, retrieved_at, type, url }

tool_use_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "web_fetch_tool_result"

caller: optional BetaDirectCaller { type } or BetaServerToolCaller { tool_id, type } or BetaServerToolCaller20260120 { tool_id, type }

Tool invocation directly from the model.

One of the following:

beta_direct_caller: object{ type }

Tool invocation directly from the model.

type: "direct"

beta_server_tool_caller: object{ tool_id, type }

Tool invocation generated by a server-side tool.

tool_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "code_execution_20250825"

beta_server_tool_caller_20260120: object{ tool_id, type }

tool_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "code_execution_20260120"

beta_advisor_tool_result_block: object{ content, tool_use_id, type }

content: BetaAdvisorToolResultError { error_code, type } or BetaAdvisorResultBlock { stop_reason, text, type } or BetaAdvisorRedactedResultBlock { encrypted_content, stop_reason, type }

One of the following:

beta_advisor_tool_result_error: object{ error_code, type }

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"

type: "advisor_tool_result_error"

beta_advisor_result_block: object{ stop_reason, text, type }

stop_reason: string

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

type: "advisor_result"

beta_advisor_redacted_result_block: object{ encrypted_content, stop_reason, type }

encrypted_content: string

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

stop_reason: string

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

type: "advisor_redacted_result"

tool_use_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "advisor_tool_result"

beta_code_execution_tool_result_block: object{ content, tool_use_id, type }

content: BetaCodeExecutionToolResultError { error_code, type } or BetaCodeExecutionResultBlock { content, return_code, stderr, 2 more } or BetaEncryptedCodeExecutionResultBlock { content, encrypted_stdout, return_code, 2 more }

Code execution result with encrypted stdout for PFC + web_search results.

One of the following:

beta_code_execution_tool_result_error: object{ error_code, type }

error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

One of the following:

"invalid_tool_input"

"unavailable"

"too_many_requests"

"execution_time_exceeded"

type: "code_execution_tool_result_error"

beta_code_execution_result_block: object{ content, return_code, stderr, 2 more }

content: array of BetaCodeExecutionOutputBlock { file_id, type }

file_id: string

type: "code_execution_output"

return_code: number

stderr: string

stdout: string

type: "code_execution_result"

beta_encrypted_code_execution_result_block: object{ content, encrypted_stdout, return_code, 2 more }

Code execution result with encrypted stdout for PFC + web_search results.

content: array of BetaCodeExecutionOutputBlock { file_id, type }

file_id: string

type: "code_execution_output"

encrypted_stdout: string

return_code: number

stderr: string

type: "encrypted_code_execution_result"

tool_use_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "code_execution_tool_result"

beta_bash_code_execution_tool_result_block: object{ content, tool_use_id, type }

content: BetaBashCodeExecutionToolResultError { error_code, type } or BetaBashCodeExecutionResultBlock { content, return_code, stderr, 2 more }

One of the following:

beta_bash_code_execution_tool_result_error: object{ error_code, type }

error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

One of the following:

"invalid_tool_input"

"unavailable"

"too_many_requests"

"execution_time_exceeded"

"output_file_too_large"

type: "bash_code_execution_tool_result_error"

beta_bash_code_execution_result_block: object{ content, return_code, stderr, 2 more }

content: array of BetaBashCodeExecutionOutputBlock { file_id, type }

file_id: string

type: "bash_code_execution_output"

return_code: number

stderr: string

stdout: string

type: "bash_code_execution_result"

tool_use_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "bash_code_execution_tool_result"

beta_text_editor_code_execution_tool_result_block: object{ content, tool_use_id, type }

content: BetaTextEditorCodeExecutionToolResultError { error_code, error_message, type } or BetaTextEditorCodeExecutionViewResultBlock { content, file_type, num_lines, 3 more } or BetaTextEditorCodeExecutionCreateResultBlock { is_file_update, type } or BetaTextEditorCodeExecutionStrReplaceResultBlock { lines, new_lines, new_start, 3 more }

One of the following:

beta_text_editor_code_execution_tool_result_error: object{ error_code, error_message, type }

error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

One of the following:

"invalid_tool_input"

"unavailable"

"too_many_requests"

"execution_time_exceeded"

"file_not_found"

error_message: string

type: "text_editor_code_execution_tool_result_error"

beta_text_editor_code_execution_view_result_block: object{ content, file_type, num_lines, 3 more }

content: string

file_type: "text" or "image" or "pdf"

One of the following:

"text"

"image"

"pdf"

num_lines: number

start_line: number

total_lines: number

type: "text_editor_code_execution_view_result"

beta_text_editor_code_execution_create_result_block: object{ is_file_update, type }

is_file_update: boolean

type: "text_editor_code_execution_create_result"

beta_text_editor_code_execution_str_replace_result_block: object{ lines, new_lines, new_start, 3 more }

lines: array of string

new_lines: number

new_start: number

old_lines: number

old_start: number

type: "text_editor_code_execution_str_replace_result"

tool_use_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "text_editor_code_execution_tool_result"

beta_tool_search_tool_result_block: object{ content, tool_use_id, type }

content: BetaToolSearchToolResultError { error_code, error_message, type } or BetaToolSearchToolSearchResultBlock { tool_references, type }

One of the following:

beta_tool_search_tool_result_error: object{ error_code, error_message, type }

error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

One of the following:

"invalid_tool_input"

"unavailable"

"too_many_requests"

"execution_time_exceeded"

error_message: string

type: "tool_search_tool_result_error"

beta_tool_search_tool_search_result_block: object{ tool_references, type }

tool_references: array of BetaToolReferenceBlock { tool_name, type }

tool_name: string

maxLength256

minLength1

pattern^[a-zA-Z0-9_-]{1,256}$

type: "tool_reference"

type: "tool_search_tool_search_result"

tool_use_id: string

pattern^srvtoolu_[a-zA-Z0-9_]+$

type: "tool_search_tool_result"

beta_mcp_tool_use_block: object{ id, input, name, 2 more }

id: string

pattern^[a-zA-Z0-9_-]+$

input: map[unknown]

The name of the MCP tool

server_name: string

The name of the MCP server

type: "mcp_tool_use"

beta_mcp_tool_result_block: object{ content, is_error, tool_use_id, type }

content: string or array of BetaTextBlock { citations, text, type }

One of the following:

union_member_0: string

beta_mcp_tool_result_block_content: array of BetaTextBlock { citations, text, type }

citations: array of BetaTextCitation

Citations supporting the text block.

One of the following:

beta_citation_char_location: object{ cited_text, document_index, document_title, 4 more }

cited_text: string

document_index: number

minimum0

document_title: string

end_char_index: number

file_id: string

start_char_index: number

minimum0

type: "char_location"

beta_citation_page_location: object{ cited_text, document_index, document_title, 4 more }

cited_text: string

document_index: number

minimum0

document_title: string

end_page_number: number

file_id: string

start_page_number: number

minimum1

type: "page_location"

beta_citation_content_block_location: object{ cited_text, document_index, document_title, 4 more }

cited_text: string

The full text of the cited block range, concatenated.

document_index: number

minimum0

document_title: string

end_block_index: number

Exclusive 0-based end index of the cited block range in the source's content array.

Always greater than start_block_index; a single-block citation has end_block_index = start_block_index + 1.

file_id: string

start_block_index: number

0-based index of the first cited block in the source's content array.

minimum0

type: "content_block_location"

beta_citations_web_search_result_location: object{ cited_text, encrypted_index, title, 2 more }

cited_text: string

encrypted_index: string

title: string

maxLength512

type: "web_search_result_location"

url: string

beta_citation_search_result_location: object{ cited_text, end_block_index, search_result_index, 4 more }

cited_text: string

The full text of the cited block range, concatenated.

end_block_index: number

Exclusive 0-based end index of the cited block range in the source's content array.

Always greater than start_block_index; a single-block citation has end_block_index = start_block_index + 1.

search_result_index: number

0-based index of the cited search result among all search_result content blocks in the request, in the order they appear across messages and tool results.

Counted separately from document_index; server-side web search results are not included in this count.

minimum0

source: string

start_block_index: number

0-based index of the first cited block in the source's content array.

minimum0

title: string

type: "search_result_location"

text: string

maxLength5000000

minLength0

type: "text"

is_error: boolean

tool_use_id: string

pattern^[a-zA-Z0-9_-]+$

type: "mcp_tool_result"

beta_container_upload_block: object{ file_id, type }

Response model for a file uploaded to the container.

file_id: string

type: "container_upload"

beta_compaction_block: object{ content, encrypted_content, type }

A compaction block returned when autocompact is triggered.

When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops.

content: string

Summary of compacted content, or null if compaction failed

encrypted_content: string

Opaque metadata from prior compaction, to be round-tripped verbatim

type: "compaction"

beta_fallback_block: object{ from, to, trigger, type }

Marks the point in content where one model's output gives way to the next.

One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a fallback_message entry in usage.iterations, not this block.

The block is treated like a server-tool content block for streaming: it arrives via the standard content_block_start / content_block_stop pair and carries no deltas.

from: object{ model }

The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its model echoes the top-level model string the caller sent (alias or canonical); when the declining hop is a fallback model, its model is that model's canonical id.

model: "claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more or string

The model that will complete your prompt.

See models for additional details and options.

One of the following:

"claude-fable-5-1"

Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows

"claude-mythos-5-1"

Our most capable model for cybersecurity and biology research, available through trusted access programs

"claude-sonnet-5"

High-performance model for coding and agents

"claude-fable-5"

Next generation of intelligence for the hardest knowledge work and coding problems

"claude-mythos-5"

Most capable model for cybersecurity and biology research

"claude-opus-5"

Powerful intelligence for long-running agents and coding

"claude-opus-4-8"

Powerful intelligence for long-running agents and coding

"claude-opus-4-7"

Powerful intelligence for long-running agents and coding

"claude-mythos-preview"

New class of intelligence, strongest in coding and cybersecurity

"claude-opus-4-6"

Powerful intelligence for long-running agents and coding

"claude-sonnet-4-6"

Best combination of speed and intelligence

"claude-haiku-4-5"

Fastest model with near-frontier intelligence

"claude-haiku-4-5-20251001"

Fastest model with near-frontier intelligence

"claude-opus-4-5"

Powerful intelligence for long-running agents and coding

"claude-opus-4-5-20251101"

Powerful intelligence for long-running agents and coding

"claude-sonnet-4-5"

High-performance model for agents and coding

"claude-sonnet-4-5-20250929"

High-performance model for agents and coding

to: object{ model }

The fallback model producing the content that follows this block. Its model is always the canonical id.

model: "claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more or string

The model that will complete your prompt.

See models for additional details and options.

One of the following:

"claude-fable-5-1"

Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows

"claude-mythos-5-1"

Our most capable model for cybersecurity and biology research, available through trusted access programs

"claude-sonnet-5"

High-performance model for coding and agents

"claude-fable-5"

Next generation of intelligence for the hardest knowledge work and coding problems

"claude-mythos-5"

Most capable model for cybersecurity and biology research

"claude-opus-5"

Powerful intelligence for long-running agents and coding

"claude-opus-4-8"

Powerful intelligence for long-running agents and coding

"claude-opus-4-7"

Powerful intelligence for long-running agents and coding

"claude-mythos-preview"

New class of intelligence, strongest in coding and cybersecurity

"claude-opus-4-6"

Powerful intelligence for long-running agents and coding

"claude-sonnet-4-6"

Best combination of speed and intelligence

"claude-haiku-4-5"

Fastest model with near-frontier intelligence

"claude-haiku-4-5-20251001"

Fastest model with near-frontier intelligence

"claude-opus-4-5"

Powerful intelligence for long-running agents and coding

"claude-opus-4-5-20251101"

Powerful intelligence for long-running agents and coding

"claude-sonnet-4-5"

High-performance model for agents and coding

"claude-sonnet-4-5-20250929"

High-performance model for agents and coding

trigger: object{ category, type }

What caused the from model to hand over at this hop.

category: "cyber" or "bio" or "frontier_llm" or 2 more

The policy category that triggered a refusal.

One of the following:

"cyber"

The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category.

"bio"

The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category.

"frontier_llm"

The request could assist the development of competing AI models, which is restricted under Anthropic's commercial terms. Benign machine learning work can also trigger this category.

"reasoning_extraction"

The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use adaptive thinking.

"general_harms"

The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category.

type: "refusal"

type: "fallback"

context_management: object{ applied_edits }

Context management response.

Information about context management strategies applied during the request.

applied_edits: array of BetaClearToolUses20250919EditResponse { cleared_input_tokens, cleared_tool_uses, type } or BetaClearThinking20251015EditResponse { cleared_input_tokens, cleared_thinking_turns, type }

List of context management edits that were applied.

One of the following:

beta_clear_tool_uses_20250919_edit_response: object{ cleared_input_tokens, cleared_tool_uses, type }

cleared_input_tokens: number

Number of input tokens cleared by this edit.

minimum0

cleared_tool_uses: number

Number of tool uses that were cleared.

minimum0

type: "clear_tool_uses_20250919"

The type of context management edit applied.

beta_clear_thinking_20251015_edit_response: object{ cleared_input_tokens, cleared_thinking_turns, type }

cleared_input_tokens: number

Number of input tokens cleared by this edit.

minimum0

cleared_thinking_turns: number

Number of thinking turns that were cleared.

minimum0

type: "clear_thinking_20251015"

The type of context management edit applied.

diagnostics: object{ cache_miss_reason }

Response envelope for request-level diagnostics. Present (possibly null) whenever the caller supplied diagnostics on the request.

cache_miss_reason: BetaCacheMissModelChanged { cache_missed_input_tokens, type } or BetaCacheMissSystemChanged { cache_missed_input_tokens, type } or BetaCacheMissToolsChanged { cache_missed_input_tokens, type } or 3 more

Explains why the prompt cache could not fully reuse the prefix from the request identified by diagnostics.previous_message_id. null means diagnosis is still pending — the response was serialized before the background comparison completed.

One of the following:

beta_cache_miss_model_changed: object{ cache_missed_input_tokens, type }

cache_missed_input_tokens: number

Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.

type: "model_changed"

beta_cache_miss_system_changed: object{ cache_missed_input_tokens, type }

cache_missed_input_tokens: number

Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.

type: "system_changed"

beta_cache_miss_tools_changed: object{ cache_missed_input_tokens, type }

cache_missed_input_tokens: number

Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.

type: "tools_changed"

beta_cache_miss_messages_changed: object{ cache_missed_input_tokens, type }

cache_missed_input_tokens: number

Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.

type: "messages_changed"

beta_cache_miss_previous_message_not_found: object{ type }

type: "previous_message_not_found"

beta_cache_miss_unavailable: object{ type }

type: "unavailable"

model: "claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more or string

The model that will complete your prompt.

See models for additional details and options.

One of the following:

"claude-fable-5-1"

Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows

"claude-mythos-5-1"

Our most capable model for cybersecurity and biology research, available through trusted access programs

"claude-sonnet-5"

High-performance model for coding and agents

"claude-fable-5"

Next generation of intelligence for the hardest knowledge work and coding problems

"claude-mythos-5"

Most capable model for cybersecurity and biology research

"claude-opus-5"

Powerful intelligence for long-running agents and coding

"claude-opus-4-8"

Powerful intelligence for long-running agents and coding

"claude-opus-4-7"

Powerful intelligence for long-running agents and coding

"claude-mythos-preview"

New class of intelligence, strongest in coding and cybersecurity

"claude-opus-4-6"

Powerful intelligence for long-running agents and coding

"claude-sonnet-4-6"

Best combination of speed and intelligence

"claude-haiku-4-5"

Fastest model with near-frontier intelligence

"claude-haiku-4-5-20251001"

Fastest model with near-frontier intelligence

"claude-opus-4-5"

Powerful intelligence for long-running agents and coding

"claude-opus-4-5-20251101"

Powerful intelligence for long-running agents and coding

"claude-sonnet-4-5"

High-performance model for agents and coding

"claude-sonnet-4-5-20250929"

High-performance model for agents and coding

role: "assistant"

Conversational role of the generated message.

This will always be "assistant".

stop_details: object{ category, explanation, fallback_credit_token, 3 more }

Structured information about a refusal.

category: "cyber" or "bio" or "frontier_llm" or 2 more

The policy category that triggered a refusal.

One of the following:

"cyber"

The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category.

"bio"

The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category.

"frontier_llm"

The request could assist the development of competing AI models, which is restricted under Anthropic's commercial terms. Benign machine learning work can also trigger this category.

"reasoning_extraction"

The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use adaptive thinking.

"general_harms"

The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category.

explanation: string

Human-readable explanation of the refusal.

This text is not guaranteed to be stable. null when no explanation is available for the category.

fallback_credit_token: string

Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as fallback_credit_token on the retry request. Expires 5 minutes after the refusal.

The retry is sent either with the same request body (system, messages, tools, and other render-shaping fields), or with the same body plus one appended assistant message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit.

null when the refused model isn't eligible for a fallback credit.

fallback_has_prefill_claim: boolean

Whether the accompanying fallback_credit_token may be redeemed with the appended-assistant retry form. Only set when fallback_credit_token is present.

true: retry by resending the same request body plus one appended assistant message whose content is this response's content with any trailing whitespace stripped from the final text block and unpaired tool_use blocks omitted (the same appended-turn shape described on fallback_credit_token), with the token attached. false: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses output_format or a tool_choice that forces tool use). One exception: when the request used output_format or a forced tool_choice and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it.

Advisory: if an appended-assistant retry is rejected with a 400 despite true, fall back to resending the original request body with the token.

recommended_model: string

The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise.

type: "refusal"

stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 5 more

The reason that we stopped.

This may be one the following values:

"end_turn": the model reached a natural stopping point
"max_tokens": we exceeded the requested max_tokens or the model's maximum
"stop_sequence": one of your provided custom stop_sequences was generated
"tool_use": the model invoked one or more tools
"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue.
"refusal": when streaming classifiers intervene to handle potential policy violations
"model_context_window_exceeded": we exceeded the model's context window

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.

One of the following:

"end_turn"

"max_tokens"

"stop_sequence"

"tool_use"

"pause_turn"

"compaction"

"refusal"

"model_context_window_exceeded"

stop_sequence: string

Which custom stop sequence was generated, if any.

This value will be a non-null string if one of your custom stop sequences was generated.

type: "message"

Object type.

For Messages, this is always "message".

usage: object{ cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 9 more }

Billing and rate-limit usage.

Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.

Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.

For example, output_tokens will be non-zero, even for an empty string response from Claude.

Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.

cache_creation: object{ ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }

Breakdown of cached tokens by TTL

ephemeral_1h_input_tokens: number

The number of input tokens used to create the 1 hour cache entry.

minimum0

ephemeral_5m_input_tokens: number

The number of input tokens used to create the 5 minute cache entry.

minimum0

cache_creation_input_tokens: number

The number of input tokens used to create the cache entry.

minimum0

cache_read_input_tokens: number

The number of input tokens read from the cache.

minimum0

fallback_credit: object{ status }

Outcome of the fallback_credit_token presented on this request.

status: BetaFallbackCreditRedeemed { type } or BetaFallbackCreditNotApplied { reason, type, remove_to_redeem }

Whether the fallback-credit reprice was applied to this response's billing.

A union discriminated on type. redeemed: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. not_applied: no reprice was applied; the arm's reason says why.

One of the following:

beta_fallback_credit_redeemed: object{ type }

The reprice was applied: the retry is billed as if the conversation had been on the retry model all along.

type: "redeemed"

beta_fallback_credit_not_applied: object{ reason, type, remove_to_redeem }

No reprice was applied; reason says why.

reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more

Why the reprice was not applied.

A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates.

One of the following:

"body_mismatch"

"continuation_excluded"

"continuation_only"

"expired"

"invalid_target_model"

"not_enabled"

"reprice_unavailable"

"temporarily_unavailable"

"variant_fields_present"

"wrong_organization"

"wrong_platform"

"wrong_workspace"

type: "not_applied"

remove_to_redeem: optional array of string

Request fields to remove before retrying, so the retry can redeem this token.

Present exactly when reason is variant_fields_present — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem.

inference_geo: string

The geographic region where inference was performed for this request.

input_tokens: number

The number of input tokens which were used.

minimum0

iterations: array of BetaMessageIterationUsage { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 4 more } or BetaCompactionIterationUsage { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 3 more } or BetaAdvisorMessageIterationUsage { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 4 more } or BetaFallbackMessageIterationUsage { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 4 more }

Per-iteration token usage breakdown.

Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by type. For message entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to:

Determine which iterations exceeded long context thresholds (>=200k tokens)
Calculate the context window size from the last message entry
Understand token accumulation across server-side tool use loops

A compaction entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a compaction entry, even when it is the last entry. A compaction entry's tokens are not included in the top-level usage fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each compaction entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results.

One of the following:

beta_message_iteration_usage: object{ cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 4 more }

Token usage for a sampling iteration.

beta_compaction_iteration_usage: object{ cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 3 more }

Token usage for a compaction iteration.

cache_creation: object{ ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }

Breakdown of cached tokens by TTL

ephemeral_1h_input_tokens: number

The number of input tokens used to create the 1 hour cache entry.

minimum0

ephemeral_5m_input_tokens: number

The number of input tokens used to create the 5 minute cache entry.

minimum0

cache_creation_input_tokens: number

The number of input tokens used to create the cache entry.

minimum0

cache_read_input_tokens: number

The number of input tokens read from the cache.

minimum0

input_tokens: number

The number of input tokens which were used.

minimum0

output_tokens: number

The number of output tokens which were used.

minimum0

type: "compaction"

Usage for a compaction iteration

beta_advisor_message_iteration_usage: object{ cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 4 more }

Token usage for an advisor sub-inference iteration.

beta_fallback_message_iteration_usage: object{ cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 4 more }

Token usage for the fallback-model attempt of a server-side fallback request.

Produced in place of a message entry for whichever hop served the response. A declined hop produces the existing message entry. Whether a fallback model served the response is signalled by the presence of this entry in usage.iterations.

output_tokens: number

The number of output tokens which were used.

minimum0

output_tokens_details: object{ thinking_tokens }

Breakdown of output tokens by category.

output_tokens remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you.

thinking_tokens: number

Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens.

Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ output_tokens; output_tokens - thinking_tokens approximates the non-reasoning output.

minimum0

server_tool_use: object{ web_fetch_requests, web_search_requests }

The number of server tool requests.

web_fetch_requests: number

The number of web fetch tool requests.

minimum0

web_search_requests: number

The number of web search tool requests.

minimum0

service_tier: "standard" or "priority" or "batch"

If the request used the priority, standard, or batch tier.

One of the following:

"standard"

"priority"

"batch"

speed: "standard" or "fast"

Inference speed mode. fast provides significantly faster output token generation at premium pricing. Not all models support fast; invalid combinations are rejected at create time.

One of the following:

"standard"

"fast"

input_transformations: optional array of BetaThinkingDroppedInputTransformation { path, reason, type }

Changes the API made to the request's input before showing it to the model: one entry per change, in request order. Today the only entry type is thinking_dropped — a thinking, redacted_thinking or connector_text block from the request's messages that was removed from the prompt instead of being shown to the model because it failed a binding check. More entry types may be added over time; ignore types you do not recognize.

Requires anthropic-beta: thinking-binding-controls-2026-08-01. Present on every such response from a model that supports extended thinking, as [] when nothing was changed; without the beta, blocks are removed all the same but nothing is reported. Removed blocks contribute nothing to usage.input_tokens. When streaming, the array is final in message_start; the final message_delta event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in message_start.

path: string

Where the removed block was in your request, as messages.{i}.content.{j}: i indexes the messages array you sent and j that message's content array — the same form error messages use.

reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"

Which binding check removed the block: model_binding_mismatch — it was created by a model whose reasoning the requested model may not read; prefix_binding_mismatch — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); organization_binding_mismatch — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; end_user_binding_mismatch — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: organization_binding_mismatch, end_user_binding_mismatch, model_binding_mismatch, prefix_binding_mismatch.

One of the following:

"model_binding_mismatch"

"prefix_binding_mismatch"

"organization_binding_mismatch"

"end_user_binding_mismatch"

type: "thinking_dropped"

Always thinking_dropped for this entry type.

type: "succeeded"

beta_message_batch_errored_result: object{ error, type }

error: object{ error, request_id, type }

error: BetaInvalidRequestError { message, type } or BetaAuthenticationError { message, type } or BetaBillingError { message, type } or 6 more

One of the following:

beta_invalid_request_error: object{ message, type }

message: string

type: "invalid_request_error"

beta_authentication_error: object{ message, type }

message: string

type: "authentication_error"

beta_billing_error: object{ message, type }

message: string

type: "billing_error"

beta_permission_error: object{ message, type }

message: string

type: "permission_error"

beta_not_found_error: object{ message, type }

message: string

type: "not_found_error"

beta_rate_limit_error: object{ message, type }

message: string

type: "rate_limit_error"

beta_gateway_timeout_error: object{ message, type }

message: string

type: "timeout_error"

beta_api_error: object{ message, type }

message: string

type: "api_error"

beta_overloaded_error: object{ message, type }

message: string

type: "overloaded_error"

request_id: string

type: "error"

type: "errored"

beta_message_batch_canceled_result: object{ type }

type: "canceled"

beta_message_batch_expired_result: object{ type }

type: "expired"

Ergebnisse eines Message Batch abrufen

ant beta:messages:batches results \
  --api-key my-anthropic-api-key \
  --message-batch-id message_batch_id