Loading...
    • Developer Guide
    • API Reference
    • MCP
    • Resources
    • Release Notes
    Search...
    ⌘K
    Using the API
    API overviewBeta headersErrors
    Messages
    Create a Message
    Count tokens in a Message
    Models
    List Models
    Get a Model
    Beta
    Create a Message
    Count tokens in a Message
    Create a Message Batch
    Retrieve a Message Batch
    List Message Batches
    Cancel a Message Batch
    Delete a Message Batch
    Retrieve Message Batch results
    Admin
    Completions
    Create a Text Completion
    Support & configuration
    Rate limitsService tiersVersionsIP addressesSupported regionsOpenAI SDK compatibility
    Console
    Log in

    Batches

    Create a Message Batch
    BetaMessageBatch beta().messages().batches().create(BatchCreateParamsparams, RequestOptionsrequestOptions = RequestOptions.none())
    POST/v1/messages/batches
    Retrieve a Message Batch
    BetaMessageBatch beta().messages().batches().retrieve(BatchRetrieveParamsparams = BatchRetrieveParams.none(), RequestOptionsrequestOptions = RequestOptions.none())
    GET/v1/messages/batches/{message_batch_id}
    List Message Batches
    BatchListPage beta().messages().batches().list(BatchListParamsparams = BatchListParams.none(), RequestOptionsrequestOptions = RequestOptions.none())
    GET/v1/messages/batches
    Cancel a Message Batch
    BetaMessageBatch beta().messages().batches().cancel(BatchCancelParamsparams = BatchCancelParams.none(), RequestOptionsrequestOptions = RequestOptions.none())
    POST/v1/messages/batches/{message_batch_id}/cancel
    Delete a Message Batch
    BetaDeletedMessageBatch beta().messages().batches().delete(BatchDeleteParamsparams = BatchDeleteParams.none(), RequestOptionsrequestOptions = RequestOptions.none())
    DELETE/v1/messages/batches/{message_batch_id}
    Retrieve Message Batch results
    BetaMessageBatchIndividualResponse beta().messages().batches().resultsStreaming(BatchResultsParamsparams = BatchResultsParams.none(), RequestOptionsrequestOptions = RequestOptions.none())
    GET/v1/messages/batches/{message_batch_id}/results
    ModelsExpand Collapse
    class BetaDeletedMessageBatch:
    String id

    ID of the Message Batch.

    JsonValue; type "message_batch_deleted"constant"message_batch_deleted"constant

    Deleted object type.

    For Message Batches, this is always "message_batch_deleted".

    class BetaMessageBatch:
    String id

    Unique object identifier.

    The format and length of IDs may change over time.

    Optional<LocalDateTime> archivedAt

    RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable.

    Optional<LocalDateTime> cancelInitiatedAt

    RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated.

    LocalDateTime createdAt

    RFC 3339 datetime string representing the time at which the Message Batch was created.

    Optional<LocalDateTime> endedAt

    RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends.

    Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired.

    formatdate-time
    LocalDateTime expiresAt

    RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation.

    ProcessingStatus processingStatus

    Processing status of the Message Batch.

    Accepts one of the following:
    IN_PROGRESS("in_progress")
    CANCELING("canceling")
    ENDED("ended")
    BetaMessageBatchRequestCounts requestCounts

    Tallies requests within the Message Batch, categorized by their status.

    Requests start as processing and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch.

    long canceled

    Number of requests in the Message Batch that have been canceled.

    This is zero until processing of the entire Message Batch has ended.

    long errored

    Number of requests in the Message Batch that encountered an error.

    This is zero until processing of the entire Message Batch has ended.

    long expired

    Number of requests in the Message Batch that have expired.

    This is zero until processing of the entire Message Batch has ended.

    long processing

    Number of requests in the Message Batch that are processing.

    long succeeded

    Number of requests in the Message Batch that have completed successfully.

    This is zero until processing of the entire Message Batch has ended.

    Optional<String> resultsUrl

    URL to a .jsonl file containing the results of the Message Batch requests. Specified only once processing ends.

    Results in the file are not guaranteed to be in the same order as requests. Use the custom_id field to match results to requests.

    JsonValue; type "message_batch"constant"message_batch"constant

    Object type.

    For Message Batches, this is always "message_batch".

    class BetaMessageBatchCanceledResult:
    JsonValue; type "canceled"constant"canceled"constant
    class BetaMessageBatchErroredResult:
    BetaErrorResponse error
    BetaError error
    Accepts one of the following:
    class BetaInvalidRequestError:
    String message
    JsonValue; type "invalid_request_error"constant"invalid_request_error"constant
    class BetaAuthenticationError:
    String message
    JsonValue; type "authentication_error"constant"authentication_error"constant
    class BetaBillingError:
    String message
    JsonValue; type "billing_error"constant"billing_error"constant
    class BetaPermissionError:
    String message
    JsonValue; type "permission_error"constant"permission_error"constant
    class BetaNotFoundError:
    String message
    JsonValue; type "not_found_error"constant"not_found_error"constant
    class BetaRateLimitError:
    String message
    JsonValue; type "rate_limit_error"constant"rate_limit_error"constant
    class BetaGatewayTimeoutError:
    String message
    JsonValue; type "timeout_error"constant"timeout_error"constant
    class BetaApiError:
    String message
    JsonValue; type "api_error"constant"api_error"constant
    class BetaOverloadedError:
    String message
    JsonValue; type "overloaded_error"constant"overloaded_error"constant
    Optional<String> requestId
    JsonValue; type "error"constant"error"constant
    JsonValue; type "errored"constant"errored"constant
    class BetaMessageBatchExpiredResult:
    JsonValue; type "expired"constant"expired"constant
    class BetaMessageBatchIndividualResponse:

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

    String customId

    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.

    BetaMessageBatchResult result

    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.

    Accepts one of the following:
    class BetaMessageBatchSucceededResult:
    BetaMessage message
    String id

    Unique object identifier.

    The format and length of IDs may change over time.

    Optional<BetaContainer> container

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

    String id

    Identifier for the container used in this request

    LocalDateTime expiresAt

    The time at which the container will expire.

    Optional<List<BetaSkill>> skills

    Skills loaded in the container

    String skillId

    Skill ID

    Type type

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

    Accepts one of the following:
    ANTHROPIC("anthropic")
    CUSTOM("custom")
    String version

    Skill version or 'latest' for most recent version

    List<BetaContentBlock> content

    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)"}]
    
    Accepts one of the following:
    class BetaTextBlock:
    Optional<List<BetaTextCitation>> citations

    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.

    Accepts one of the following:
    class BetaCitationCharLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endCharIndex
    Optional<String> fileId
    long startCharIndex
    JsonValue; type "char_location"constant"char_location"constant
    class BetaCitationPageLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endPageNumber
    Optional<String> fileId
    long startPageNumber
    JsonValue; type "page_location"constant"page_location"constant
    class BetaCitationContentBlockLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endBlockIndex
    Optional<String> fileId
    long startBlockIndex
    JsonValue; type "content_block_location"constant"content_block_location"constant
    class BetaCitationsWebSearchResultLocation:
    String citedText
    String encryptedIndex
    Optional<String> title
    JsonValue; type "web_search_result_location"constant"web_search_result_location"constant
    String url
    class BetaCitationSearchResultLocation:
    String citedText
    long endBlockIndex
    long searchResultIndex
    String source
    long startBlockIndex
    Optional<String> title
    JsonValue; type "search_result_location"constant"search_result_location"constant
    String text
    JsonValue; type "text"constant"text"constant
    class BetaThinkingBlock:
    String signature
    String thinking
    JsonValue; type "thinking"constant"thinking"constant
    class BetaRedactedThinkingBlock:
    String data
    JsonValue; type "redacted_thinking"constant"redacted_thinking"constant
    class BetaToolUseBlock:
    String id
    Input input
    String name
    JsonValue; type "tool_use"constant"tool_use"constant
    Optional<Caller> caller

    Tool invocation directly from the model.

    Accepts one of the following:
    class BetaDirectCaller:

    Tool invocation directly from the model.

    JsonValue; type "direct"constant"direct"constant
    class BetaServerToolCaller:

    Tool invocation generated by a server-side tool.

    String toolId
    JsonValue; type "code_execution_20250825"constant"code_execution_20250825"constant
    class BetaServerToolCaller20260120:
    String toolId
    JsonValue; type "code_execution_20260120"constant"code_execution_20260120"constant
    class BetaServerToolUseBlock:
    String id
    Input input
    Name name
    Accepts one of the following:
    WEB_SEARCH("web_search")
    WEB_FETCH("web_fetch")
    CODE_EXECUTION("code_execution")
    BASH_CODE_EXECUTION("bash_code_execution")
    TEXT_EDITOR_CODE_EXECUTION("text_editor_code_execution")
    TOOL_SEARCH_TOOL_REGEX("tool_search_tool_regex")
    TOOL_SEARCH_TOOL_BM25("tool_search_tool_bm25")
    JsonValue; type "server_tool_use"constant"server_tool_use"constant
    Optional<Caller> caller

    Tool invocation directly from the model.

    Accepts one of the following:
    class BetaDirectCaller:

    Tool invocation directly from the model.

    JsonValue; type "direct"constant"direct"constant
    class BetaServerToolCaller:

    Tool invocation generated by a server-side tool.

    String toolId
    JsonValue; type "code_execution_20250825"constant"code_execution_20250825"constant
    class BetaServerToolCaller20260120:
    String toolId
    JsonValue; type "code_execution_20260120"constant"code_execution_20260120"constant
    class BetaWebSearchToolResultBlock:
    BetaWebSearchToolResultBlockContent content
    Accepts one of the following:
    class BetaWebSearchToolResultError:
    BetaWebSearchToolResultErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    MAX_USES_EXCEEDED("max_uses_exceeded")
    TOO_MANY_REQUESTS("too_many_requests")
    QUERY_TOO_LONG("query_too_long")
    REQUEST_TOO_LARGE("request_too_large")
    JsonValue; type "web_search_tool_result_error"constant"web_search_tool_result_error"constant
    List<BetaWebSearchResultBlock>
    String encryptedContent
    Optional<String> pageAge
    String title
    JsonValue; type "web_search_result"constant"web_search_result"constant
    String url
    String toolUseId
    JsonValue; type "web_search_tool_result"constant"web_search_tool_result"constant
    Optional<Caller> caller

    Tool invocation directly from the model.

    Accepts one of the following:
    class BetaDirectCaller:

    Tool invocation directly from the model.

    JsonValue; type "direct"constant"direct"constant
    class BetaServerToolCaller:

    Tool invocation generated by a server-side tool.

    String toolId
    JsonValue; type "code_execution_20250825"constant"code_execution_20250825"constant
    class BetaServerToolCaller20260120:
    String toolId
    JsonValue; type "code_execution_20260120"constant"code_execution_20260120"constant
    class BetaWebFetchToolResultBlock:
    Content content
    Accepts one of the following:
    class BetaWebFetchToolResultErrorBlock:
    BetaWebFetchToolResultErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    URL_TOO_LONG("url_too_long")
    URL_NOT_ALLOWED("url_not_allowed")
    URL_NOT_ACCESSIBLE("url_not_accessible")
    UNSUPPORTED_CONTENT_TYPE("unsupported_content_type")
    TOO_MANY_REQUESTS("too_many_requests")
    MAX_USES_EXCEEDED("max_uses_exceeded")
    UNAVAILABLE("unavailable")
    JsonValue; type "web_fetch_tool_result_error"constant"web_fetch_tool_result_error"constant
    class BetaWebFetchBlock:
    BetaDocumentBlock content
    Optional<BetaCitationConfig> citations

    Citation configuration for the document

    boolean enabled
    Source source
    Accepts one of the following:
    class BetaBase64PdfSource:
    String data
    JsonValue; mediaType "application/pdf"constant"application/pdf"constant
    JsonValue; type "base64"constant"base64"constant
    class BetaPlainTextSource:
    String data
    JsonValue; mediaType "text/plain"constant"text/plain"constant
    JsonValue; type "text"constant"text"constant
    Optional<String> title

    The title of the document

    JsonValue; type "document"constant"document"constant
    Optional<String> retrievedAt

    ISO 8601 timestamp when the content was retrieved

    JsonValue; type "web_fetch_result"constant"web_fetch_result"constant
    String url

    Fetched content URL

    String toolUseId
    JsonValue; type "web_fetch_tool_result"constant"web_fetch_tool_result"constant
    Optional<Caller> caller

    Tool invocation directly from the model.

    Accepts one of the following:
    class BetaDirectCaller:

    Tool invocation directly from the model.

    JsonValue; type "direct"constant"direct"constant
    class BetaServerToolCaller:

    Tool invocation generated by a server-side tool.

    String toolId
    JsonValue; type "code_execution_20250825"constant"code_execution_20250825"constant
    class BetaServerToolCaller20260120:
    String toolId
    JsonValue; type "code_execution_20260120"constant"code_execution_20260120"constant
    class BetaCodeExecutionToolResultBlock:
    BetaCodeExecutionToolResultBlockContent content

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

    Accepts one of the following:
    class BetaCodeExecutionToolResultError:
    BetaCodeExecutionToolResultErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    TOO_MANY_REQUESTS("too_many_requests")
    EXECUTION_TIME_EXCEEDED("execution_time_exceeded")
    JsonValue; type "code_execution_tool_result_error"constant"code_execution_tool_result_error"constant
    class BetaCodeExecutionResultBlock:
    List<BetaCodeExecutionOutputBlock> content
    String fileId
    JsonValue; type "code_execution_output"constant"code_execution_output"constant
    long returnCode
    String stderr
    String stdout
    JsonValue; type "code_execution_result"constant"code_execution_result"constant
    class BetaEncryptedCodeExecutionResultBlock:

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

    List<BetaCodeExecutionOutputBlock> content
    String fileId
    JsonValue; type "code_execution_output"constant"code_execution_output"constant
    String encryptedStdout
    long returnCode
    String stderr
    JsonValue; type "encrypted_code_execution_result"constant"encrypted_code_execution_result"constant
    String toolUseId
    JsonValue; type "code_execution_tool_result"constant"code_execution_tool_result"constant
    class BetaBashCodeExecutionToolResultBlock:
    Content content
    Accepts one of the following:
    class BetaBashCodeExecutionToolResultError:
    ErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    TOO_MANY_REQUESTS("too_many_requests")
    EXECUTION_TIME_EXCEEDED("execution_time_exceeded")
    OUTPUT_FILE_TOO_LARGE("output_file_too_large")
    JsonValue; type "bash_code_execution_tool_result_error"constant"bash_code_execution_tool_result_error"constant
    class BetaBashCodeExecutionResultBlock:
    List<BetaBashCodeExecutionOutputBlock> content
    String fileId
    JsonValue; type "bash_code_execution_output"constant"bash_code_execution_output"constant
    long returnCode
    String stderr
    String stdout
    JsonValue; type "bash_code_execution_result"constant"bash_code_execution_result"constant
    String toolUseId
    JsonValue; type "bash_code_execution_tool_result"constant"bash_code_execution_tool_result"constant
    class BetaTextEditorCodeExecutionToolResultBlock:
    Content content
    Accepts one of the following:
    class BetaTextEditorCodeExecutionToolResultError:
    ErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    TOO_MANY_REQUESTS("too_many_requests")
    EXECUTION_TIME_EXCEEDED("execution_time_exceeded")
    FILE_NOT_FOUND("file_not_found")
    Optional<String> errorMessage
    JsonValue; type "text_editor_code_execution_tool_result_error"constant"text_editor_code_execution_tool_result_error"constant
    class BetaTextEditorCodeExecutionViewResultBlock:
    String content
    FileType fileType
    Accepts one of the following:
    TEXT("text")
    IMAGE("image")
    PDF("pdf")
    Optional<Long> numLines
    Optional<Long> startLine
    Optional<Long> totalLines
    JsonValue; type "text_editor_code_execution_view_result"constant"text_editor_code_execution_view_result"constant
    class BetaTextEditorCodeExecutionCreateResultBlock:
    boolean isFileUpdate
    JsonValue; type "text_editor_code_execution_create_result"constant"text_editor_code_execution_create_result"constant
    class BetaTextEditorCodeExecutionStrReplaceResultBlock:
    Optional<List<String>> lines
    Optional<Long> newLines
    Optional<Long> newStart
    Optional<Long> oldLines
    Optional<Long> oldStart
    JsonValue; type "text_editor_code_execution_str_replace_result"constant"text_editor_code_execution_str_replace_result"constant
    String toolUseId
    JsonValue; type "text_editor_code_execution_tool_result"constant"text_editor_code_execution_tool_result"constant
    class BetaToolSearchToolResultBlock:
    Content content
    Accepts one of the following:
    class BetaToolSearchToolResultError:
    ErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    TOO_MANY_REQUESTS("too_many_requests")
    EXECUTION_TIME_EXCEEDED("execution_time_exceeded")
    Optional<String> errorMessage
    JsonValue; type "tool_search_tool_result_error"constant"tool_search_tool_result_error"constant
    class BetaToolSearchToolSearchResultBlock:
    List<BetaToolReferenceBlock> toolReferences
    String toolName
    JsonValue; type "tool_reference"constant"tool_reference"constant
    JsonValue; type "tool_search_tool_search_result"constant"tool_search_tool_search_result"constant
    String toolUseId
    JsonValue; type "tool_search_tool_result"constant"tool_search_tool_result"constant
    class BetaMcpToolUseBlock:
    String id
    Input input
    String name

    The name of the MCP tool

    String serverName

    The name of the MCP server

    JsonValue; type "mcp_tool_use"constant"mcp_tool_use"constant
    class BetaMcpToolResultBlock:
    Content content
    Accepts one of the following:
    String
    List<BetaTextBlock>
    Optional<List<BetaTextCitation>> citations

    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.

    Accepts one of the following:
    class BetaCitationCharLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endCharIndex
    Optional<String> fileId
    long startCharIndex
    JsonValue; type "char_location"constant"char_location"constant
    class BetaCitationPageLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endPageNumber
    Optional<String> fileId
    long startPageNumber
    JsonValue; type "page_location"constant"page_location"constant
    class BetaCitationContentBlockLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endBlockIndex
    Optional<String> fileId
    long startBlockIndex
    JsonValue; type "content_block_location"constant"content_block_location"constant
    class BetaCitationsWebSearchResultLocation:
    String citedText
    String encryptedIndex
    Optional<String> title
    JsonValue; type "web_search_result_location"constant"web_search_result_location"constant
    String url
    class BetaCitationSearchResultLocation:
    String citedText
    long endBlockIndex
    long searchResultIndex
    String source
    long startBlockIndex
    Optional<String> title
    JsonValue; type "search_result_location"constant"search_result_location"constant
    String text
    JsonValue; type "text"constant"text"constant
    boolean isError
    String toolUseId
    JsonValue; type "mcp_tool_result"constant"mcp_tool_result"constant
    class BetaContainerUploadBlock:

    Response model for a file uploaded to the container.

    String fileId
    JsonValue; type "container_upload"constant"container_upload"constant
    class BetaCompactionBlock:

    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.

    Optional<String> content

    Summary of compacted content, or null if compaction failed

    JsonValue; type "compaction"constant"compaction"constant
    Optional<BetaContextManagementResponse> contextManagement

    Context management response.

    Information about context management strategies applied during the request.

    List<AppliedEdit> appliedEdits

    List of context management edits that were applied.

    Accepts one of the following:
    class BetaClearToolUses20250919EditResponse:
    long clearedInputTokens

    Number of input tokens cleared by this edit.

    long clearedToolUses

    Number of tool uses that were cleared.

    JsonValue; type "clear_tool_uses_20250919"constant"clear_tool_uses_20250919"constant

    The type of context management edit applied.

    class BetaClearThinking20251015EditResponse:
    long clearedInputTokens

    Number of input tokens cleared by this edit.

    long clearedThinkingTurns

    Number of thinking turns that were cleared.

    JsonValue; type "clear_thinking_20251015"constant"clear_thinking_20251015"constant

    The type of context management edit applied.

    Model model

    The model that will complete your prompt.

    See models for additional details and options.

    Accepts one of the following:
    CLAUDE_OPUS_4_6("claude-opus-4-6")

    Most intelligent model for building agents and coding

    CLAUDE_SONNET_4_6("claude-sonnet-4-6")

    Frontier intelligence at scale — built for coding, agents, and enterprise workflows

    CLAUDE_OPUS_4_5_20251101("claude-opus-4-5-20251101")

    Premium model combining maximum intelligence with practical performance

    CLAUDE_OPUS_4_5("claude-opus-4-5")

    Premium model combining maximum intelligence with practical performance

    CLAUDE_3_7_SONNET_LATEST("claude-3-7-sonnet-latest")

    High-performance model with early extended thinking

    CLAUDE_3_7_SONNET_20250219("claude-3-7-sonnet-20250219")

    High-performance model with early extended thinking

    CLAUDE_3_5_HAIKU_LATEST("claude-3-5-haiku-latest")

    Fastest and most compact model for near-instant responsiveness

    CLAUDE_3_5_HAIKU_20241022("claude-3-5-haiku-20241022")

    Our fastest model

    CLAUDE_HAIKU_4_5("claude-haiku-4-5")

    Hybrid model, capable of near-instant responses and extended thinking

    CLAUDE_HAIKU_4_5_20251001("claude-haiku-4-5-20251001")

    Hybrid model, capable of near-instant responses and extended thinking

    CLAUDE_SONNET_4_20250514("claude-sonnet-4-20250514")

    High-performance model with extended thinking

    CLAUDE_SONNET_4_0("claude-sonnet-4-0")

    High-performance model with extended thinking

    CLAUDE_4_SONNET_20250514("claude-4-sonnet-20250514")

    High-performance model with extended thinking

    CLAUDE_SONNET_4_5("claude-sonnet-4-5")

    Our best model for real-world agents and coding

    CLAUDE_SONNET_4_5_20250929("claude-sonnet-4-5-20250929")

    Our best model for real-world agents and coding

    CLAUDE_OPUS_4_0("claude-opus-4-0")

    Our most capable model

    CLAUDE_OPUS_4_20250514("claude-opus-4-20250514")

    Our most capable model

    CLAUDE_4_OPUS_20250514("claude-4-opus-20250514")

    Our most capable model

    CLAUDE_OPUS_4_1_20250805("claude-opus-4-1-20250805")

    Our most capable model

    CLAUDE_3_OPUS_LATEST("claude-3-opus-latest")

    Excels at writing and complex tasks

    CLAUDE_3_OPUS_20240229("claude-3-opus-20240229")

    Excels at writing and complex tasks

    CLAUDE_3_HAIKU_20240307("claude-3-haiku-20240307")

    Our previous most fast and cost-effective

    JsonValue; role "assistant"constant"assistant"constant

    Conversational role of the generated message.

    This will always be "assistant".

    Optional<BetaStopReason> stopReason

    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

    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.

    Accepts one of the following:
    END_TURN("end_turn")
    MAX_TOKENS("max_tokens")
    STOP_SEQUENCE("stop_sequence")
    TOOL_USE("tool_use")
    PAUSE_TURN("pause_turn")
    COMPACTION("compaction")
    REFUSAL("refusal")
    MODEL_CONTEXT_WINDOW_EXCEEDED("model_context_window_exceeded")
    Optional<String> stopSequence

    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.

    JsonValue; type "message"constant"message"constant

    Object type.

    For Messages, this is always "message".

    BetaUsage usage

    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.

    Optional<BetaCacheCreation> cacheCreation

    Breakdown of cached tokens by TTL

    long ephemeral1hInputTokens

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

    long ephemeral5mInputTokens

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

    Optional<Long> cacheCreationInputTokens

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

    Optional<Long> cacheReadInputTokens

    The number of input tokens read from the cache.

    Optional<String> inferenceGeo

    The geographic region where inference was performed for this request.

    long inputTokens

    The number of input tokens which were used.

    Optional<List<BetaIterationsUsageItems>> iterations

    Per-iteration token usage breakdown.

    Each entry represents one sampling iteration, with its own input/output token counts and cache statistics. This allows you to:

    • Determine which iterations exceeded long context thresholds (>=200k tokens)
    • Calculate the true context window size from the last iteration
    • Understand token accumulation across server-side tool use loops
    Accepts one of the following:
    class BetaMessageIterationUsage:

    Token usage for a sampling iteration.

    Optional<BetaCacheCreation> cacheCreation

    Breakdown of cached tokens by TTL

    long ephemeral1hInputTokens

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

    long ephemeral5mInputTokens

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

    long cacheCreationInputTokens

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

    long cacheReadInputTokens

    The number of input tokens read from the cache.

    long inputTokens

    The number of input tokens which were used.

    long outputTokens

    The number of output tokens which were used.

    JsonValue; type "message"constant"message"constant

    Usage for a sampling iteration

    class BetaCompactionIterationUsage:

    Token usage for a compaction iteration.

    Optional<BetaCacheCreation> cacheCreation

    Breakdown of cached tokens by TTL

    long ephemeral1hInputTokens

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

    long ephemeral5mInputTokens

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

    long cacheCreationInputTokens

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

    long cacheReadInputTokens

    The number of input tokens read from the cache.

    long inputTokens

    The number of input tokens which were used.

    long outputTokens

    The number of output tokens which were used.

    JsonValue; type "compaction"constant"compaction"constant

    Usage for a compaction iteration

    long outputTokens

    The number of output tokens which were used.

    Optional<BetaServerToolUsage> serverToolUse

    The number of server tool requests.

    long webFetchRequests

    The number of web fetch tool requests.

    long webSearchRequests

    The number of web search tool requests.

    Optional<ServiceTier> serviceTier

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

    Accepts one of the following:
    STANDARD("standard")
    PRIORITY("priority")
    BATCH("batch")
    Optional<Speed> speed

    The inference speed mode used for this request.

    Accepts one of the following:
    STANDARD("standard")
    FAST("fast")
    JsonValue; type "succeeded"constant"succeeded"constant
    class BetaMessageBatchErroredResult:
    BetaErrorResponse error
    BetaError error
    Accepts one of the following:
    class BetaInvalidRequestError:
    String message
    JsonValue; type "invalid_request_error"constant"invalid_request_error"constant
    class BetaAuthenticationError:
    String message
    JsonValue; type "authentication_error"constant"authentication_error"constant
    class BetaBillingError:
    String message
    JsonValue; type "billing_error"constant"billing_error"constant
    class BetaPermissionError:
    String message
    JsonValue; type "permission_error"constant"permission_error"constant
    class BetaNotFoundError:
    String message
    JsonValue; type "not_found_error"constant"not_found_error"constant
    class BetaRateLimitError:
    String message
    JsonValue; type "rate_limit_error"constant"rate_limit_error"constant
    class BetaGatewayTimeoutError:
    String message
    JsonValue; type "timeout_error"constant"timeout_error"constant
    class BetaApiError:
    String message
    JsonValue; type "api_error"constant"api_error"constant
    class BetaOverloadedError:
    String message
    JsonValue; type "overloaded_error"constant"overloaded_error"constant
    Optional<String> requestId
    JsonValue; type "error"constant"error"constant
    JsonValue; type "errored"constant"errored"constant
    class BetaMessageBatchCanceledResult:
    JsonValue; type "canceled"constant"canceled"constant
    class BetaMessageBatchExpiredResult:
    JsonValue; type "expired"constant"expired"constant
    class BetaMessageBatchRequestCounts:
    long canceled

    Number of requests in the Message Batch that have been canceled.

    This is zero until processing of the entire Message Batch has ended.

    long errored

    Number of requests in the Message Batch that encountered an error.

    This is zero until processing of the entire Message Batch has ended.

    long expired

    Number of requests in the Message Batch that have expired.

    This is zero until processing of the entire Message Batch has ended.

    long processing

    Number of requests in the Message Batch that are processing.

    long succeeded

    Number of requests in the Message Batch that have completed successfully.

    This is zero until processing of the entire Message Batch has ended.

    class BetaMessageBatchResult: A class that can be one of several variants.union

    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.

    class BetaMessageBatchSucceededResult:
    BetaMessage message
    String id

    Unique object identifier.

    The format and length of IDs may change over time.

    Optional<BetaContainer> container

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

    String id

    Identifier for the container used in this request

    LocalDateTime expiresAt

    The time at which the container will expire.

    Optional<List<BetaSkill>> skills

    Skills loaded in the container

    String skillId

    Skill ID

    Type type

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

    Accepts one of the following:
    ANTHROPIC("anthropic")
    CUSTOM("custom")
    String version

    Skill version or 'latest' for most recent version

    List<BetaContentBlock> content

    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)"}]
    
    Accepts one of the following:
    class BetaTextBlock:
    Optional<List<BetaTextCitation>> citations

    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.

    Accepts one of the following:
    class BetaCitationCharLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endCharIndex
    Optional<String> fileId
    long startCharIndex
    JsonValue; type "char_location"constant"char_location"constant
    class BetaCitationPageLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endPageNumber
    Optional<String> fileId
    long startPageNumber
    JsonValue; type "page_location"constant"page_location"constant
    class BetaCitationContentBlockLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endBlockIndex
    Optional<String> fileId
    long startBlockIndex
    JsonValue; type "content_block_location"constant"content_block_location"constant
    class BetaCitationsWebSearchResultLocation:
    String citedText
    String encryptedIndex
    Optional<String> title
    JsonValue; type "web_search_result_location"constant"web_search_result_location"constant
    String url
    class BetaCitationSearchResultLocation:
    String citedText
    long endBlockIndex
    long searchResultIndex
    String source
    long startBlockIndex
    Optional<String> title
    JsonValue; type "search_result_location"constant"search_result_location"constant
    String text
    JsonValue; type "text"constant"text"constant
    class BetaThinkingBlock:
    String signature
    String thinking
    JsonValue; type "thinking"constant"thinking"constant
    class BetaRedactedThinkingBlock:
    String data
    JsonValue; type "redacted_thinking"constant"redacted_thinking"constant
    class BetaToolUseBlock:
    String id
    Input input
    String name
    JsonValue; type "tool_use"constant"tool_use"constant
    Optional<Caller> caller

    Tool invocation directly from the model.

    Accepts one of the following:
    class BetaDirectCaller:

    Tool invocation directly from the model.

    JsonValue; type "direct"constant"direct"constant
    class BetaServerToolCaller:

    Tool invocation generated by a server-side tool.

    String toolId
    JsonValue; type "code_execution_20250825"constant"code_execution_20250825"constant
    class BetaServerToolCaller20260120:
    String toolId
    JsonValue; type "code_execution_20260120"constant"code_execution_20260120"constant
    class BetaServerToolUseBlock:
    String id
    Input input
    Name name
    Accepts one of the following:
    WEB_SEARCH("web_search")
    WEB_FETCH("web_fetch")
    CODE_EXECUTION("code_execution")
    BASH_CODE_EXECUTION("bash_code_execution")
    TEXT_EDITOR_CODE_EXECUTION("text_editor_code_execution")
    TOOL_SEARCH_TOOL_REGEX("tool_search_tool_regex")
    TOOL_SEARCH_TOOL_BM25("tool_search_tool_bm25")
    JsonValue; type "server_tool_use"constant"server_tool_use"constant
    Optional<Caller> caller

    Tool invocation directly from the model.

    Accepts one of the following:
    class BetaDirectCaller:

    Tool invocation directly from the model.

    JsonValue; type "direct"constant"direct"constant
    class BetaServerToolCaller:

    Tool invocation generated by a server-side tool.

    String toolId
    JsonValue; type "code_execution_20250825"constant"code_execution_20250825"constant
    class BetaServerToolCaller20260120:
    String toolId
    JsonValue; type "code_execution_20260120"constant"code_execution_20260120"constant
    class BetaWebSearchToolResultBlock:
    BetaWebSearchToolResultBlockContent content
    Accepts one of the following:
    class BetaWebSearchToolResultError:
    BetaWebSearchToolResultErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    MAX_USES_EXCEEDED("max_uses_exceeded")
    TOO_MANY_REQUESTS("too_many_requests")
    QUERY_TOO_LONG("query_too_long")
    REQUEST_TOO_LARGE("request_too_large")
    JsonValue; type "web_search_tool_result_error"constant"web_search_tool_result_error"constant
    List<BetaWebSearchResultBlock>
    String encryptedContent
    Optional<String> pageAge
    String title
    JsonValue; type "web_search_result"constant"web_search_result"constant
    String url
    String toolUseId
    JsonValue; type "web_search_tool_result"constant"web_search_tool_result"constant
    Optional<Caller> caller

    Tool invocation directly from the model.

    Accepts one of the following:
    class BetaDirectCaller:

    Tool invocation directly from the model.

    JsonValue; type "direct"constant"direct"constant
    class BetaServerToolCaller:

    Tool invocation generated by a server-side tool.

    String toolId
    JsonValue; type "code_execution_20250825"constant"code_execution_20250825"constant
    class BetaServerToolCaller20260120:
    String toolId
    JsonValue; type "code_execution_20260120"constant"code_execution_20260120"constant
    class BetaWebFetchToolResultBlock:
    Content content
    Accepts one of the following:
    class BetaWebFetchToolResultErrorBlock:
    BetaWebFetchToolResultErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    URL_TOO_LONG("url_too_long")
    URL_NOT_ALLOWED("url_not_allowed")
    URL_NOT_ACCESSIBLE("url_not_accessible")
    UNSUPPORTED_CONTENT_TYPE("unsupported_content_type")
    TOO_MANY_REQUESTS("too_many_requests")
    MAX_USES_EXCEEDED("max_uses_exceeded")
    UNAVAILABLE("unavailable")
    JsonValue; type "web_fetch_tool_result_error"constant"web_fetch_tool_result_error"constant
    class BetaWebFetchBlock:
    BetaDocumentBlock content
    Optional<BetaCitationConfig> citations

    Citation configuration for the document

    boolean enabled
    Source source
    Accepts one of the following:
    class BetaBase64PdfSource:
    String data
    JsonValue; mediaType "application/pdf"constant"application/pdf"constant
    JsonValue; type "base64"constant"base64"constant
    class BetaPlainTextSource:
    String data
    JsonValue; mediaType "text/plain"constant"text/plain"constant
    JsonValue; type "text"constant"text"constant
    Optional<String> title

    The title of the document

    JsonValue; type "document"constant"document"constant
    Optional<String> retrievedAt

    ISO 8601 timestamp when the content was retrieved

    JsonValue; type "web_fetch_result"constant"web_fetch_result"constant
    String url

    Fetched content URL

    String toolUseId
    JsonValue; type "web_fetch_tool_result"constant"web_fetch_tool_result"constant
    Optional<Caller> caller

    Tool invocation directly from the model.

    Accepts one of the following:
    class BetaDirectCaller:

    Tool invocation directly from the model.

    JsonValue; type "direct"constant"direct"constant
    class BetaServerToolCaller:

    Tool invocation generated by a server-side tool.

    String toolId
    JsonValue; type "code_execution_20250825"constant"code_execution_20250825"constant
    class BetaServerToolCaller20260120:
    String toolId
    JsonValue; type "code_execution_20260120"constant"code_execution_20260120"constant
    class BetaCodeExecutionToolResultBlock:
    BetaCodeExecutionToolResultBlockContent content

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

    Accepts one of the following:
    class BetaCodeExecutionToolResultError:
    BetaCodeExecutionToolResultErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    TOO_MANY_REQUESTS("too_many_requests")
    EXECUTION_TIME_EXCEEDED("execution_time_exceeded")
    JsonValue; type "code_execution_tool_result_error"constant"code_execution_tool_result_error"constant
    class BetaCodeExecutionResultBlock:
    List<BetaCodeExecutionOutputBlock> content
    String fileId
    JsonValue; type "code_execution_output"constant"code_execution_output"constant
    long returnCode
    String stderr
    String stdout
    JsonValue; type "code_execution_result"constant"code_execution_result"constant
    class BetaEncryptedCodeExecutionResultBlock:

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

    List<BetaCodeExecutionOutputBlock> content
    String fileId
    JsonValue; type "code_execution_output"constant"code_execution_output"constant
    String encryptedStdout
    long returnCode
    String stderr
    JsonValue; type "encrypted_code_execution_result"constant"encrypted_code_execution_result"constant
    String toolUseId
    JsonValue; type "code_execution_tool_result"constant"code_execution_tool_result"constant
    class BetaBashCodeExecutionToolResultBlock:
    Content content
    Accepts one of the following:
    class BetaBashCodeExecutionToolResultError:
    ErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    TOO_MANY_REQUESTS("too_many_requests")
    EXECUTION_TIME_EXCEEDED("execution_time_exceeded")
    OUTPUT_FILE_TOO_LARGE("output_file_too_large")
    JsonValue; type "bash_code_execution_tool_result_error"constant"bash_code_execution_tool_result_error"constant
    class BetaBashCodeExecutionResultBlock:
    List<BetaBashCodeExecutionOutputBlock> content
    String fileId
    JsonValue; type "bash_code_execution_output"constant"bash_code_execution_output"constant
    long returnCode
    String stderr
    String stdout
    JsonValue; type "bash_code_execution_result"constant"bash_code_execution_result"constant
    String toolUseId
    JsonValue; type "bash_code_execution_tool_result"constant"bash_code_execution_tool_result"constant
    class BetaTextEditorCodeExecutionToolResultBlock:
    Content content
    Accepts one of the following:
    class BetaTextEditorCodeExecutionToolResultError:
    ErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    TOO_MANY_REQUESTS("too_many_requests")
    EXECUTION_TIME_EXCEEDED("execution_time_exceeded")
    FILE_NOT_FOUND("file_not_found")
    Optional<String> errorMessage
    JsonValue; type "text_editor_code_execution_tool_result_error"constant"text_editor_code_execution_tool_result_error"constant
    class BetaTextEditorCodeExecutionViewResultBlock:
    String content
    FileType fileType
    Accepts one of the following:
    TEXT("text")
    IMAGE("image")
    PDF("pdf")
    Optional<Long> numLines
    Optional<Long> startLine
    Optional<Long> totalLines
    JsonValue; type "text_editor_code_execution_view_result"constant"text_editor_code_execution_view_result"constant
    class BetaTextEditorCodeExecutionCreateResultBlock:
    boolean isFileUpdate
    JsonValue; type "text_editor_code_execution_create_result"constant"text_editor_code_execution_create_result"constant
    class BetaTextEditorCodeExecutionStrReplaceResultBlock:
    Optional<List<String>> lines
    Optional<Long> newLines
    Optional<Long> newStart
    Optional<Long> oldLines
    Optional<Long> oldStart
    JsonValue; type "text_editor_code_execution_str_replace_result"constant"text_editor_code_execution_str_replace_result"constant
    String toolUseId
    JsonValue; type "text_editor_code_execution_tool_result"constant"text_editor_code_execution_tool_result"constant
    class BetaToolSearchToolResultBlock:
    Content content
    Accepts one of the following:
    class BetaToolSearchToolResultError:
    ErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    TOO_MANY_REQUESTS("too_many_requests")
    EXECUTION_TIME_EXCEEDED("execution_time_exceeded")
    Optional<String> errorMessage
    JsonValue; type "tool_search_tool_result_error"constant"tool_search_tool_result_error"constant
    class BetaToolSearchToolSearchResultBlock:
    List<BetaToolReferenceBlock> toolReferences
    String toolName
    JsonValue; type "tool_reference"constant"tool_reference"constant
    JsonValue; type "tool_search_tool_search_result"constant"tool_search_tool_search_result"constant
    String toolUseId
    JsonValue; type "tool_search_tool_result"constant"tool_search_tool_result"constant
    class BetaMcpToolUseBlock:
    String id
    Input input
    String name

    The name of the MCP tool

    String serverName

    The name of the MCP server

    JsonValue; type "mcp_tool_use"constant"mcp_tool_use"constant
    class BetaMcpToolResultBlock:
    Content content
    Accepts one of the following:
    String
    List<BetaTextBlock>
    Optional<List<BetaTextCitation>> citations

    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.

    Accepts one of the following:
    class BetaCitationCharLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endCharIndex
    Optional<String> fileId
    long startCharIndex
    JsonValue; type "char_location"constant"char_location"constant
    class BetaCitationPageLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endPageNumber
    Optional<String> fileId
    long startPageNumber
    JsonValue; type "page_location"constant"page_location"constant
    class BetaCitationContentBlockLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endBlockIndex
    Optional<String> fileId
    long startBlockIndex
    JsonValue; type "content_block_location"constant"content_block_location"constant
    class BetaCitationsWebSearchResultLocation:
    String citedText
    String encryptedIndex
    Optional<String> title
    JsonValue; type "web_search_result_location"constant"web_search_result_location"constant
    String url
    class BetaCitationSearchResultLocation:
    String citedText
    long endBlockIndex
    long searchResultIndex
    String source
    long startBlockIndex
    Optional<String> title
    JsonValue; type "search_result_location"constant"search_result_location"constant
    String text
    JsonValue; type "text"constant"text"constant
    boolean isError
    String toolUseId
    JsonValue; type "mcp_tool_result"constant"mcp_tool_result"constant
    class BetaContainerUploadBlock:

    Response model for a file uploaded to the container.

    String fileId
    JsonValue; type "container_upload"constant"container_upload"constant
    class BetaCompactionBlock:

    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.

    Optional<String> content

    Summary of compacted content, or null if compaction failed

    JsonValue; type "compaction"constant"compaction"constant
    Optional<BetaContextManagementResponse> contextManagement

    Context management response.

    Information about context management strategies applied during the request.

    List<AppliedEdit> appliedEdits

    List of context management edits that were applied.

    Accepts one of the following:
    class BetaClearToolUses20250919EditResponse:
    long clearedInputTokens

    Number of input tokens cleared by this edit.

    long clearedToolUses

    Number of tool uses that were cleared.

    JsonValue; type "clear_tool_uses_20250919"constant"clear_tool_uses_20250919"constant

    The type of context management edit applied.

    class BetaClearThinking20251015EditResponse:
    long clearedInputTokens

    Number of input tokens cleared by this edit.

    long clearedThinkingTurns

    Number of thinking turns that were cleared.

    JsonValue; type "clear_thinking_20251015"constant"clear_thinking_20251015"constant

    The type of context management edit applied.

    Model model

    The model that will complete your prompt.

    See models for additional details and options.

    Accepts one of the following:
    CLAUDE_OPUS_4_6("claude-opus-4-6")

    Most intelligent model for building agents and coding

    CLAUDE_SONNET_4_6("claude-sonnet-4-6")

    Frontier intelligence at scale — built for coding, agents, and enterprise workflows

    CLAUDE_OPUS_4_5_20251101("claude-opus-4-5-20251101")

    Premium model combining maximum intelligence with practical performance

    CLAUDE_OPUS_4_5("claude-opus-4-5")

    Premium model combining maximum intelligence with practical performance

    CLAUDE_3_7_SONNET_LATEST("claude-3-7-sonnet-latest")

    High-performance model with early extended thinking

    CLAUDE_3_7_SONNET_20250219("claude-3-7-sonnet-20250219")

    High-performance model with early extended thinking

    CLAUDE_3_5_HAIKU_LATEST("claude-3-5-haiku-latest")

    Fastest and most compact model for near-instant responsiveness

    CLAUDE_3_5_HAIKU_20241022("claude-3-5-haiku-20241022")

    Our fastest model

    CLAUDE_HAIKU_4_5("claude-haiku-4-5")

    Hybrid model, capable of near-instant responses and extended thinking

    CLAUDE_HAIKU_4_5_20251001("claude-haiku-4-5-20251001")

    Hybrid model, capable of near-instant responses and extended thinking

    CLAUDE_SONNET_4_20250514("claude-sonnet-4-20250514")

    High-performance model with extended thinking

    CLAUDE_SONNET_4_0("claude-sonnet-4-0")

    High-performance model with extended thinking

    CLAUDE_4_SONNET_20250514("claude-4-sonnet-20250514")

    High-performance model with extended thinking

    CLAUDE_SONNET_4_5("claude-sonnet-4-5")

    Our best model for real-world agents and coding

    CLAUDE_SONNET_4_5_20250929("claude-sonnet-4-5-20250929")

    Our best model for real-world agents and coding

    CLAUDE_OPUS_4_0("claude-opus-4-0")

    Our most capable model

    CLAUDE_OPUS_4_20250514("claude-opus-4-20250514")

    Our most capable model

    CLAUDE_4_OPUS_20250514("claude-4-opus-20250514")

    Our most capable model

    CLAUDE_OPUS_4_1_20250805("claude-opus-4-1-20250805")

    Our most capable model

    CLAUDE_3_OPUS_LATEST("claude-3-opus-latest")

    Excels at writing and complex tasks

    CLAUDE_3_OPUS_20240229("claude-3-opus-20240229")

    Excels at writing and complex tasks

    CLAUDE_3_HAIKU_20240307("claude-3-haiku-20240307")

    Our previous most fast and cost-effective

    JsonValue; role "assistant"constant"assistant"constant

    Conversational role of the generated message.

    This will always be "assistant".

    Optional<BetaStopReason> stopReason

    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

    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.

    Accepts one of the following:
    END_TURN("end_turn")
    MAX_TOKENS("max_tokens")
    STOP_SEQUENCE("stop_sequence")
    TOOL_USE("tool_use")
    PAUSE_TURN("pause_turn")
    COMPACTION("compaction")
    REFUSAL("refusal")
    MODEL_CONTEXT_WINDOW_EXCEEDED("model_context_window_exceeded")
    Optional<String> stopSequence

    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.

    JsonValue; type "message"constant"message"constant

    Object type.

    For Messages, this is always "message".

    BetaUsage usage

    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.

    Optional<BetaCacheCreation> cacheCreation

    Breakdown of cached tokens by TTL

    long ephemeral1hInputTokens

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

    long ephemeral5mInputTokens

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

    Optional<Long> cacheCreationInputTokens

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

    Optional<Long> cacheReadInputTokens

    The number of input tokens read from the cache.

    Optional<String> inferenceGeo

    The geographic region where inference was performed for this request.

    long inputTokens

    The number of input tokens which were used.

    Optional<List<BetaIterationsUsageItems>> iterations

    Per-iteration token usage breakdown.

    Each entry represents one sampling iteration, with its own input/output token counts and cache statistics. This allows you to:

    • Determine which iterations exceeded long context thresholds (>=200k tokens)
    • Calculate the true context window size from the last iteration
    • Understand token accumulation across server-side tool use loops
    Accepts one of the following:
    class BetaMessageIterationUsage:

    Token usage for a sampling iteration.

    Optional<BetaCacheCreation> cacheCreation

    Breakdown of cached tokens by TTL

    long ephemeral1hInputTokens

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

    long ephemeral5mInputTokens

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

    long cacheCreationInputTokens

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

    long cacheReadInputTokens

    The number of input tokens read from the cache.

    long inputTokens

    The number of input tokens which were used.

    long outputTokens

    The number of output tokens which were used.

    JsonValue; type "message"constant"message"constant

    Usage for a sampling iteration

    class BetaCompactionIterationUsage:

    Token usage for a compaction iteration.

    Optional<BetaCacheCreation> cacheCreation

    Breakdown of cached tokens by TTL

    long ephemeral1hInputTokens

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

    long ephemeral5mInputTokens

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

    long cacheCreationInputTokens

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

    long cacheReadInputTokens

    The number of input tokens read from the cache.

    long inputTokens

    The number of input tokens which were used.

    long outputTokens

    The number of output tokens which were used.

    JsonValue; type "compaction"constant"compaction"constant

    Usage for a compaction iteration

    long outputTokens

    The number of output tokens which were used.

    Optional<BetaServerToolUsage> serverToolUse

    The number of server tool requests.

    long webFetchRequests

    The number of web fetch tool requests.

    long webSearchRequests

    The number of web search tool requests.

    Optional<ServiceTier> serviceTier

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

    Accepts one of the following:
    STANDARD("standard")
    PRIORITY("priority")
    BATCH("batch")
    Optional<Speed> speed

    The inference speed mode used for this request.

    Accepts one of the following:
    STANDARD("standard")
    FAST("fast")
    JsonValue; type "succeeded"constant"succeeded"constant
    class BetaMessageBatchErroredResult:
    BetaErrorResponse error
    BetaError error
    Accepts one of the following:
    class BetaInvalidRequestError:
    String message
    JsonValue; type "invalid_request_error"constant"invalid_request_error"constant
    class BetaAuthenticationError:
    String message
    JsonValue; type "authentication_error"constant"authentication_error"constant
    class BetaBillingError:
    String message
    JsonValue; type "billing_error"constant"billing_error"constant
    class BetaPermissionError:
    String message
    JsonValue; type "permission_error"constant"permission_error"constant
    class BetaNotFoundError:
    String message
    JsonValue; type "not_found_error"constant"not_found_error"constant
    class BetaRateLimitError:
    String message
    JsonValue; type "rate_limit_error"constant"rate_limit_error"constant
    class BetaGatewayTimeoutError:
    String message
    JsonValue; type "timeout_error"constant"timeout_error"constant
    class BetaApiError:
    String message
    JsonValue; type "api_error"constant"api_error"constant
    class BetaOverloadedError:
    String message
    JsonValue; type "overloaded_error"constant"overloaded_error"constant
    Optional<String> requestId
    JsonValue; type "error"constant"error"constant
    JsonValue; type "errored"constant"errored"constant
    class BetaMessageBatchCanceledResult:
    JsonValue; type "canceled"constant"canceled"constant
    class BetaMessageBatchExpiredResult:
    JsonValue; type "expired"constant"expired"constant
    class BetaMessageBatchSucceededResult:
    BetaMessage message
    String id

    Unique object identifier.

    The format and length of IDs may change over time.

    Optional<BetaContainer> container

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

    String id

    Identifier for the container used in this request

    LocalDateTime expiresAt

    The time at which the container will expire.

    Optional<List<BetaSkill>> skills

    Skills loaded in the container

    String skillId

    Skill ID

    Type type

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

    Accepts one of the following:
    ANTHROPIC("anthropic")
    CUSTOM("custom")
    String version

    Skill version or 'latest' for most recent version

    List<BetaContentBlock> content

    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)"}]
    
    Accepts one of the following:
    class BetaTextBlock:
    Optional<List<BetaTextCitation>> citations

    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.

    Accepts one of the following:
    class BetaCitationCharLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endCharIndex
    Optional<String> fileId
    long startCharIndex
    JsonValue; type "char_location"constant"char_location"constant
    class BetaCitationPageLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endPageNumber
    Optional<String> fileId
    long startPageNumber
    JsonValue; type "page_location"constant"page_location"constant
    class BetaCitationContentBlockLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endBlockIndex
    Optional<String> fileId
    long startBlockIndex
    JsonValue; type "content_block_location"constant"content_block_location"constant
    class BetaCitationsWebSearchResultLocation:
    String citedText
    String encryptedIndex
    Optional<String> title
    JsonValue; type "web_search_result_location"constant"web_search_result_location"constant
    String url
    class BetaCitationSearchResultLocation:
    String citedText
    long endBlockIndex
    long searchResultIndex
    String source
    long startBlockIndex
    Optional<String> title
    JsonValue; type "search_result_location"constant"search_result_location"constant
    String text
    JsonValue; type "text"constant"text"constant
    class BetaThinkingBlock:
    String signature
    String thinking
    JsonValue; type "thinking"constant"thinking"constant
    class BetaRedactedThinkingBlock:
    String data
    JsonValue; type "redacted_thinking"constant"redacted_thinking"constant
    class BetaToolUseBlock:
    String id
    Input input
    String name
    JsonValue; type "tool_use"constant"tool_use"constant
    Optional<Caller> caller

    Tool invocation directly from the model.

    Accepts one of the following:
    class BetaDirectCaller:

    Tool invocation directly from the model.

    JsonValue; type "direct"constant"direct"constant
    class BetaServerToolCaller:

    Tool invocation generated by a server-side tool.

    String toolId
    JsonValue; type "code_execution_20250825"constant"code_execution_20250825"constant
    class BetaServerToolCaller20260120:
    String toolId
    JsonValue; type "code_execution_20260120"constant"code_execution_20260120"constant
    class BetaServerToolUseBlock:
    String id
    Input input
    Name name
    Accepts one of the following:
    WEB_SEARCH("web_search")
    WEB_FETCH("web_fetch")
    CODE_EXECUTION("code_execution")
    BASH_CODE_EXECUTION("bash_code_execution")
    TEXT_EDITOR_CODE_EXECUTION("text_editor_code_execution")
    TOOL_SEARCH_TOOL_REGEX("tool_search_tool_regex")
    TOOL_SEARCH_TOOL_BM25("tool_search_tool_bm25")
    JsonValue; type "server_tool_use"constant"server_tool_use"constant
    Optional<Caller> caller

    Tool invocation directly from the model.

    Accepts one of the following:
    class BetaDirectCaller:

    Tool invocation directly from the model.

    JsonValue; type "direct"constant"direct"constant
    class BetaServerToolCaller:

    Tool invocation generated by a server-side tool.

    String toolId
    JsonValue; type "code_execution_20250825"constant"code_execution_20250825"constant
    class BetaServerToolCaller20260120:
    String toolId
    JsonValue; type "code_execution_20260120"constant"code_execution_20260120"constant
    class BetaWebSearchToolResultBlock:
    BetaWebSearchToolResultBlockContent content
    Accepts one of the following:
    class BetaWebSearchToolResultError:
    BetaWebSearchToolResultErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    MAX_USES_EXCEEDED("max_uses_exceeded")
    TOO_MANY_REQUESTS("too_many_requests")
    QUERY_TOO_LONG("query_too_long")
    REQUEST_TOO_LARGE("request_too_large")
    JsonValue; type "web_search_tool_result_error"constant"web_search_tool_result_error"constant
    List<BetaWebSearchResultBlock>
    String encryptedContent
    Optional<String> pageAge
    String title
    JsonValue; type "web_search_result"constant"web_search_result"constant
    String url
    String toolUseId
    JsonValue; type "web_search_tool_result"constant"web_search_tool_result"constant
    Optional<Caller> caller

    Tool invocation directly from the model.

    Accepts one of the following:
    class BetaDirectCaller:

    Tool invocation directly from the model.

    JsonValue; type "direct"constant"direct"constant
    class BetaServerToolCaller:

    Tool invocation generated by a server-side tool.

    String toolId
    JsonValue; type "code_execution_20250825"constant"code_execution_20250825"constant
    class BetaServerToolCaller20260120:
    String toolId
    JsonValue; type "code_execution_20260120"constant"code_execution_20260120"constant
    class BetaWebFetchToolResultBlock:
    Content content
    Accepts one of the following:
    class BetaWebFetchToolResultErrorBlock:
    BetaWebFetchToolResultErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    URL_TOO_LONG("url_too_long")
    URL_NOT_ALLOWED("url_not_allowed")
    URL_NOT_ACCESSIBLE("url_not_accessible")
    UNSUPPORTED_CONTENT_TYPE("unsupported_content_type")
    TOO_MANY_REQUESTS("too_many_requests")
    MAX_USES_EXCEEDED("max_uses_exceeded")
    UNAVAILABLE("unavailable")
    JsonValue; type "web_fetch_tool_result_error"constant"web_fetch_tool_result_error"constant
    class BetaWebFetchBlock:
    BetaDocumentBlock content
    Optional<BetaCitationConfig> citations

    Citation configuration for the document

    boolean enabled
    Source source
    Accepts one of the following:
    class BetaBase64PdfSource:
    String data
    JsonValue; mediaType "application/pdf"constant"application/pdf"constant
    JsonValue; type "base64"constant"base64"constant
    class BetaPlainTextSource:
    String data
    JsonValue; mediaType "text/plain"constant"text/plain"constant
    JsonValue; type "text"constant"text"constant
    Optional<String> title

    The title of the document

    JsonValue; type "document"constant"document"constant
    Optional<String> retrievedAt

    ISO 8601 timestamp when the content was retrieved

    JsonValue; type "web_fetch_result"constant"web_fetch_result"constant
    String url

    Fetched content URL

    String toolUseId
    JsonValue; type "web_fetch_tool_result"constant"web_fetch_tool_result"constant
    Optional<Caller> caller

    Tool invocation directly from the model.

    Accepts one of the following:
    class BetaDirectCaller:

    Tool invocation directly from the model.

    JsonValue; type "direct"constant"direct"constant
    class BetaServerToolCaller:

    Tool invocation generated by a server-side tool.

    String toolId
    JsonValue; type "code_execution_20250825"constant"code_execution_20250825"constant
    class BetaServerToolCaller20260120:
    String toolId
    JsonValue; type "code_execution_20260120"constant"code_execution_20260120"constant
    class BetaCodeExecutionToolResultBlock:
    BetaCodeExecutionToolResultBlockContent content

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

    Accepts one of the following:
    class BetaCodeExecutionToolResultError:
    BetaCodeExecutionToolResultErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    TOO_MANY_REQUESTS("too_many_requests")
    EXECUTION_TIME_EXCEEDED("execution_time_exceeded")
    JsonValue; type "code_execution_tool_result_error"constant"code_execution_tool_result_error"constant
    class BetaCodeExecutionResultBlock:
    List<BetaCodeExecutionOutputBlock> content
    String fileId
    JsonValue; type "code_execution_output"constant"code_execution_output"constant
    long returnCode
    String stderr
    String stdout
    JsonValue; type "code_execution_result"constant"code_execution_result"constant
    class BetaEncryptedCodeExecutionResultBlock:

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

    List<BetaCodeExecutionOutputBlock> content
    String fileId
    JsonValue; type "code_execution_output"constant"code_execution_output"constant
    String encryptedStdout
    long returnCode
    String stderr
    JsonValue; type "encrypted_code_execution_result"constant"encrypted_code_execution_result"constant
    String toolUseId
    JsonValue; type "code_execution_tool_result"constant"code_execution_tool_result"constant
    class BetaBashCodeExecutionToolResultBlock:
    Content content
    Accepts one of the following:
    class BetaBashCodeExecutionToolResultError:
    ErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    TOO_MANY_REQUESTS("too_many_requests")
    EXECUTION_TIME_EXCEEDED("execution_time_exceeded")
    OUTPUT_FILE_TOO_LARGE("output_file_too_large")
    JsonValue; type "bash_code_execution_tool_result_error"constant"bash_code_execution_tool_result_error"constant
    class BetaBashCodeExecutionResultBlock:
    List<BetaBashCodeExecutionOutputBlock> content
    String fileId
    JsonValue; type "bash_code_execution_output"constant"bash_code_execution_output"constant
    long returnCode
    String stderr
    String stdout
    JsonValue; type "bash_code_execution_result"constant"bash_code_execution_result"constant
    String toolUseId
    JsonValue; type "bash_code_execution_tool_result"constant"bash_code_execution_tool_result"constant
    class BetaTextEditorCodeExecutionToolResultBlock:
    Content content
    Accepts one of the following:
    class BetaTextEditorCodeExecutionToolResultError:
    ErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    TOO_MANY_REQUESTS("too_many_requests")
    EXECUTION_TIME_EXCEEDED("execution_time_exceeded")
    FILE_NOT_FOUND("file_not_found")
    Optional<String> errorMessage
    JsonValue; type "text_editor_code_execution_tool_result_error"constant"text_editor_code_execution_tool_result_error"constant
    class BetaTextEditorCodeExecutionViewResultBlock:
    String content
    FileType fileType
    Accepts one of the following:
    TEXT("text")
    IMAGE("image")
    PDF("pdf")
    Optional<Long> numLines
    Optional<Long> startLine
    Optional<Long> totalLines
    JsonValue; type "text_editor_code_execution_view_result"constant"text_editor_code_execution_view_result"constant
    class BetaTextEditorCodeExecutionCreateResultBlock:
    boolean isFileUpdate
    JsonValue; type "text_editor_code_execution_create_result"constant"text_editor_code_execution_create_result"constant
    class BetaTextEditorCodeExecutionStrReplaceResultBlock:
    Optional<List<String>> lines
    Optional<Long> newLines
    Optional<Long> newStart
    Optional<Long> oldLines
    Optional<Long> oldStart
    JsonValue; type "text_editor_code_execution_str_replace_result"constant"text_editor_code_execution_str_replace_result"constant
    String toolUseId
    JsonValue; type "text_editor_code_execution_tool_result"constant"text_editor_code_execution_tool_result"constant
    class BetaToolSearchToolResultBlock:
    Content content
    Accepts one of the following:
    class BetaToolSearchToolResultError:
    ErrorCode errorCode
    Accepts one of the following:
    INVALID_TOOL_INPUT("invalid_tool_input")
    UNAVAILABLE("unavailable")
    TOO_MANY_REQUESTS("too_many_requests")
    EXECUTION_TIME_EXCEEDED("execution_time_exceeded")
    Optional<String> errorMessage
    JsonValue; type "tool_search_tool_result_error"constant"tool_search_tool_result_error"constant
    class BetaToolSearchToolSearchResultBlock:
    List<BetaToolReferenceBlock> toolReferences
    String toolName
    JsonValue; type "tool_reference"constant"tool_reference"constant
    JsonValue; type "tool_search_tool_search_result"constant"tool_search_tool_search_result"constant
    String toolUseId
    JsonValue; type "tool_search_tool_result"constant"tool_search_tool_result"constant
    class BetaMcpToolUseBlock:
    String id
    Input input
    String name

    The name of the MCP tool

    String serverName

    The name of the MCP server

    JsonValue; type "mcp_tool_use"constant"mcp_tool_use"constant
    class BetaMcpToolResultBlock:
    Content content
    Accepts one of the following:
    String
    List<BetaTextBlock>
    Optional<List<BetaTextCitation>> citations

    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.

    Accepts one of the following:
    class BetaCitationCharLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endCharIndex
    Optional<String> fileId
    long startCharIndex
    JsonValue; type "char_location"constant"char_location"constant
    class BetaCitationPageLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endPageNumber
    Optional<String> fileId
    long startPageNumber
    JsonValue; type "page_location"constant"page_location"constant
    class BetaCitationContentBlockLocation:
    String citedText
    long documentIndex
    Optional<String> documentTitle
    long endBlockIndex
    Optional<String> fileId
    long startBlockIndex
    JsonValue; type "content_block_location"constant"content_block_location"constant
    class BetaCitationsWebSearchResultLocation:
    String citedText
    String encryptedIndex
    Optional<String> title
    JsonValue; type "web_search_result_location"constant"web_search_result_location"constant
    String url
    class BetaCitationSearchResultLocation:
    String citedText
    long endBlockIndex
    long searchResultIndex
    String source
    long startBlockIndex
    Optional<String> title
    JsonValue; type "search_result_location"constant"search_result_location"constant
    String text
    JsonValue; type "text"constant"text"constant
    boolean isError
    String toolUseId
    JsonValue; type "mcp_tool_result"constant"mcp_tool_result"constant
    class BetaContainerUploadBlock:

    Response model for a file uploaded to the container.

    String fileId
    JsonValue; type "container_upload"constant"container_upload"constant
    class BetaCompactionBlock:

    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.

    Optional<String> content

    Summary of compacted content, or null if compaction failed

    JsonValue; type "compaction"constant"compaction"constant
    Optional<BetaContextManagementResponse> contextManagement

    Context management response.

    Information about context management strategies applied during the request.

    List<AppliedEdit> appliedEdits

    List of context management edits that were applied.

    Accepts one of the following:
    class BetaClearToolUses20250919EditResponse:
    long clearedInputTokens

    Number of input tokens cleared by this edit.

    long clearedToolUses

    Number of tool uses that were cleared.

    JsonValue; type "clear_tool_uses_20250919"constant"clear_tool_uses_20250919"constant

    The type of context management edit applied.

    class BetaClearThinking20251015EditResponse:
    long clearedInputTokens

    Number of input tokens cleared by this edit.

    long clearedThinkingTurns

    Number of thinking turns that were cleared.

    JsonValue; type "clear_thinking_20251015"constant"clear_thinking_20251015"constant

    The type of context management edit applied.

    Model model

    The model that will complete your prompt.

    See models for additional details and options.

    Accepts one of the following:
    CLAUDE_OPUS_4_6("claude-opus-4-6")

    Most intelligent model for building agents and coding

    CLAUDE_SONNET_4_6("claude-sonnet-4-6")

    Frontier intelligence at scale — built for coding, agents, and enterprise workflows

    CLAUDE_OPUS_4_5_20251101("claude-opus-4-5-20251101")

    Premium model combining maximum intelligence with practical performance

    CLAUDE_OPUS_4_5("claude-opus-4-5")

    Premium model combining maximum intelligence with practical performance

    CLAUDE_3_7_SONNET_LATEST("claude-3-7-sonnet-latest")

    High-performance model with early extended thinking

    CLAUDE_3_7_SONNET_20250219("claude-3-7-sonnet-20250219")

    High-performance model with early extended thinking

    CLAUDE_3_5_HAIKU_LATEST("claude-3-5-haiku-latest")

    Fastest and most compact model for near-instant responsiveness

    CLAUDE_3_5_HAIKU_20241022("claude-3-5-haiku-20241022")

    Our fastest model

    CLAUDE_HAIKU_4_5("claude-haiku-4-5")

    Hybrid model, capable of near-instant responses and extended thinking

    CLAUDE_HAIKU_4_5_20251001("claude-haiku-4-5-20251001")

    Hybrid model, capable of near-instant responses and extended thinking

    CLAUDE_SONNET_4_20250514("claude-sonnet-4-20250514")

    High-performance model with extended thinking

    CLAUDE_SONNET_4_0("claude-sonnet-4-0")

    High-performance model with extended thinking

    CLAUDE_4_SONNET_20250514("claude-4-sonnet-20250514")

    High-performance model with extended thinking

    CLAUDE_SONNET_4_5("claude-sonnet-4-5")

    Our best model for real-world agents and coding

    CLAUDE_SONNET_4_5_20250929("claude-sonnet-4-5-20250929")

    Our best model for real-world agents and coding

    CLAUDE_OPUS_4_0("claude-opus-4-0")

    Our most capable model

    CLAUDE_OPUS_4_20250514("claude-opus-4-20250514")

    Our most capable model

    CLAUDE_4_OPUS_20250514("claude-4-opus-20250514")

    Our most capable model

    CLAUDE_OPUS_4_1_20250805("claude-opus-4-1-20250805")

    Our most capable model

    CLAUDE_3_OPUS_LATEST("claude-3-opus-latest")

    Excels at writing and complex tasks

    CLAUDE_3_OPUS_20240229("claude-3-opus-20240229")

    Excels at writing and complex tasks

    CLAUDE_3_HAIKU_20240307("claude-3-haiku-20240307")

    Our previous most fast and cost-effective

    JsonValue; role "assistant"constant"assistant"constant

    Conversational role of the generated message.

    This will always be "assistant".

    Optional<BetaStopReason> stopReason

    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

    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.

    Accepts one of the following:
    END_TURN("end_turn")
    MAX_TOKENS("max_tokens")
    STOP_SEQUENCE("stop_sequence")
    TOOL_USE("tool_use")
    PAUSE_TURN("pause_turn")
    COMPACTION("compaction")
    REFUSAL("refusal")
    MODEL_CONTEXT_WINDOW_EXCEEDED("model_context_window_exceeded")
    Optional<String> stopSequence

    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.

    JsonValue; type "message"constant"message"constant

    Object type.

    For Messages, this is always "message".

    BetaUsage usage

    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.

    Optional<BetaCacheCreation> cacheCreation

    Breakdown of cached tokens by TTL

    long ephemeral1hInputTokens

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

    long ephemeral5mInputTokens

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

    Optional<Long> cacheCreationInputTokens

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

    Optional<Long> cacheReadInputTokens

    The number of input tokens read from the cache.

    Optional<String> inferenceGeo

    The geographic region where inference was performed for this request.

    long inputTokens

    The number of input tokens which were used.

    Optional<List<BetaIterationsUsageItems>> iterations

    Per-iteration token usage breakdown.

    Each entry represents one sampling iteration, with its own input/output token counts and cache statistics. This allows you to:

    • Determine which iterations exceeded long context thresholds (>=200k tokens)
    • Calculate the true context window size from the last iteration
    • Understand token accumulation across server-side tool use loops
    Accepts one of the following:
    class BetaMessageIterationUsage:

    Token usage for a sampling iteration.

    Optional<BetaCacheCreation> cacheCreation

    Breakdown of cached tokens by TTL

    long ephemeral1hInputTokens

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

    long ephemeral5mInputTokens

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

    long cacheCreationInputTokens

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

    long cacheReadInputTokens

    The number of input tokens read from the cache.

    long inputTokens

    The number of input tokens which were used.

    long outputTokens

    The number of output tokens which were used.

    JsonValue; type "message"constant"message"constant

    Usage for a sampling iteration

    class BetaCompactionIterationUsage:

    Token usage for a compaction iteration.

    Optional<BetaCacheCreation> cacheCreation

    Breakdown of cached tokens by TTL

    long ephemeral1hInputTokens

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

    long ephemeral5mInputTokens

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

    long cacheCreationInputTokens

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

    long cacheReadInputTokens

    The number of input tokens read from the cache.

    long inputTokens

    The number of input tokens which were used.

    long outputTokens

    The number of output tokens which were used.

    JsonValue; type "compaction"constant"compaction"constant

    Usage for a compaction iteration

    long outputTokens

    The number of output tokens which were used.

    Optional<BetaServerToolUsage> serverToolUse

    The number of server tool requests.

    long webFetchRequests

    The number of web fetch tool requests.

    long webSearchRequests

    The number of web search tool requests.

    Optional<ServiceTier> serviceTier

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

    Accepts one of the following:
    STANDARD("standard")
    PRIORITY("priority")
    BATCH("batch")
    Optional<Speed> speed

    The inference speed mode used for this request.

    Accepts one of the following:
    STANDARD("standard")
    FAST("fast")
    JsonValue; type "succeeded"constant"succeeded"constant

    Solutions

    • AI agents
    • Code modernization
    • Coding
    • Customer support
    • Education
    • Financial services
    • Government
    • Life sciences

    Partners

    • Amazon Bedrock
    • Google Cloud's Vertex AI

    Learn

    • Blog
    • Catalog
    • Courses
    • Use cases
    • Connectors
    • Customer stories
    • Engineering at Anthropic
    • Events
    • Powered by Claude
    • Service partners
    • Startups program

    Company

    • Anthropic
    • Careers
    • Economic Futures
    • Research
    • News
    • Responsible Scaling Policy
    • Security and compliance
    • Transparency

    Learn

    • Blog
    • Catalog
    • Courses
    • Use cases
    • Connectors
    • Customer stories
    • Engineering at Anthropic
    • Events
    • Powered by Claude
    • Service partners
    • Startups program

    Help and security

    • Availability
    • Status
    • Support
    • Discord

    Terms and policies

    • Privacy policy
    • Responsible disclosure policy
    • Terms of service: Commercial
    • Terms of service: Consumer
    • Usage policy