## Retrieve Message Batch results

`BetaMessageBatchIndividualResponse Beta.Messages.Batches.ResultsStreaming(BatchResultsParamsparameters, CancellationTokencancellationToken = default)`

**get** `/v1/messages/batches/{message_batch_id}/results`

Streams the results of a Message Batch as a `.jsonl` file.

Each line in the file is a JSON object containing the result of a single request in the Message Batch. Results are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests.

Learn more about the Message Batches API in our [user guide](https://docs.claude.com/en/docs/build-with-claude/batch-processing)

### Parameters

- `BatchResultsParams parameters`

  - `required string messageBatchID`

    ID of the Message Batch.

  - `IReadOnlyList<AnthropicBeta> betas`

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

    - `"message-batches-2024-09-24"MessageBatches2024_09_24`

    - `"prompt-caching-2024-07-31"PromptCaching2024_07_31`

    - `"computer-use-2024-10-22"ComputerUse2024_10_22`

    - `"computer-use-2025-01-24"ComputerUse2025_01_24`

    - `"pdfs-2024-09-25"Pdfs2024_09_25`

    - `"token-counting-2024-11-01"TokenCounting2024_11_01`

    - `"token-efficient-tools-2025-02-19"TokenEfficientTools2025_02_19`

    - `"output-128k-2025-02-19"Output128k2025_02_19`

    - `"files-api-2025-04-14"FilesApi2025_04_14`

    - `"mcp-client-2025-04-04"McpClient2025_04_04`

    - `"mcp-client-2025-11-20"McpClient2025_11_20`

    - `"dev-full-thinking-2025-05-14"DevFullThinking2025_05_14`

    - `"interleaved-thinking-2025-05-14"InterleavedThinking2025_05_14`

    - `"code-execution-2025-05-22"CodeExecution2025_05_22`

    - `"extended-cache-ttl-2025-04-11"ExtendedCacheTtl2025_04_11`

    - `"context-1m-2025-08-07"Context1m2025_08_07`

    - `"context-management-2025-06-27"ContextManagement2025_06_27`

    - `"model-context-window-exceeded-2025-08-26"ModelContextWindowExceeded2025_08_26`

    - `"skills-2025-10-02"Skills2025_10_02`

    - `"fast-mode-2026-02-01"FastMode2026_02_01`

    - `"output-300k-2026-03-24"Output300k2026_03_24`

    - `"user-profiles-2026-03-24"UserProfiles2026_03_24`

    - `"advisor-tool-2026-03-01"AdvisorTool2026_03_01`

    - `"managed-agents-2026-04-01"ManagedAgents2026_04_01`

    - `"cache-diagnosis-2026-04-07"CacheDiagnosis2026_04_07`

    - `"thinking-token-count-2026-05-13"ThinkingTokenCount2026_05_13`

    - `"server-side-fallback-2026-06-01"ServerSideFallback2026_06_01`

    - `"fallback-credit-2026-06-01"FallbackCredit2026_06_01`

### Returns

- `class BetaMessageBatchIndividualResponse:`

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

  - `required 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.

  - `required 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.

    - `class BetaMessageBatchSucceededResult:`

      - `required BetaMessage Message`

        - `required string ID`

          Unique object identifier.

          The format and length of IDs may change over time.

        - `required BetaContainer? Container`

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

          - `required string ID`

            Identifier for the container used in this request

          - `required DateTimeOffset ExpiresAt`

            The time at which the container will expire.

          - `required IReadOnlyList<BetaSkill>? Skills`

            Skills loaded in the container

            - `required string SkillID`

              Skill ID

            - `required Type Type`

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

              - `"anthropic"Anthropic`

              - `"custom"Custom`

            - `required string Version`

              Skill version or 'latest' for most recent version

        - `required IReadOnlyList<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:

          ```json
          [{"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:

          ```json
          [
            {"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:

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

          - `class BetaTextBlock:`

            - `required IReadOnlyList<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`.

              - `class BetaCitationCharLocation:`

                - `required string CitedText`

                - `required Long DocumentIndex`

                - `required string? DocumentTitle`

                - `required Long EndCharIndex`

                - `required string? FileID`

                - `required Long StartCharIndex`

                - `JsonElement Type "char_location"constant`

              - `class BetaCitationPageLocation:`

                - `required string CitedText`

                - `required Long DocumentIndex`

                - `required string? DocumentTitle`

                - `required Long EndPageNumber`

                - `required string? FileID`

                - `required Long StartPageNumber`

                - `JsonElement Type "page_location"constant`

              - `class BetaCitationContentBlockLocation:`

                - `required string CitedText`

                  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.

                - `required Long DocumentIndex`

                - `required string? DocumentTitle`

                - `required Long EndBlockIndex`

                  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`.

                - `required string? FileID`

                - `required Long StartBlockIndex`

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

                - `JsonElement Type "content_block_location"constant`

              - `class BetaCitationsWebSearchResultLocation:`

                - `required string CitedText`

                - `required string EncryptedIndex`

                - `required string? Title`

                - `JsonElement Type "web_search_result_location"constant`

                - `required string Url`

              - `class BetaCitationSearchResultLocation:`

                - `required string CitedText`

                  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.

                - `required Long EndBlockIndex`

                  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`.

                - `required Long SearchResultIndex`

                  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.

                - `required string Source`

                - `required Long StartBlockIndex`

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

                - `required string? Title`

                - `JsonElement Type "search_result_location"constant`

            - `required string Text`

            - `JsonElement Type "text"constant`

          - `class BetaThinkingBlock:`

            - `required string Signature`

            - `required string Thinking`

            - `JsonElement Type "thinking"constant`

          - `class BetaRedactedThinkingBlock:`

            - `required string Data`

            - `JsonElement Type "redacted_thinking"constant`

          - `class BetaToolUseBlock:`

            - `required string ID`

            - `required IReadOnlyDictionary<string, JsonElement> Input`

            - `required string Name`

            - `JsonElement Type "tool_use"constant`

            - `Caller Caller`

              Tool invocation directly from the model.

              - `class BetaDirectCaller:`

                Tool invocation directly from the model.

                - `JsonElement Type "direct"constant`

              - `class BetaServerToolCaller:`

                Tool invocation generated by a server-side tool.

                - `required string ToolID`

                - `JsonElement Type "code_execution_20250825"constant`

              - `class BetaServerToolCaller20260120:`

                - `required string ToolID`

                - `JsonElement Type "code_execution_20260120"constant`

          - `class BetaServerToolUseBlock:`

            - `required string ID`

            - `required IReadOnlyDictionary<string, JsonElement> Input`

            - `required Name Name`

              - `"advisor"Advisor`

              - `"web_search"WebSearch`

              - `"web_fetch"WebFetch`

              - `"code_execution"CodeExecution`

              - `"bash_code_execution"BashCodeExecution`

              - `"text_editor_code_execution"TextEditorCodeExecution`

              - `"tool_search_tool_regex"ToolSearchToolRegex`

              - `"tool_search_tool_bm25"ToolSearchToolBm25`

            - `JsonElement Type "server_tool_use"constant`

            - `Caller Caller`

              Tool invocation directly from the model.

              - `class BetaDirectCaller:`

                Tool invocation directly from the model.

              - `class BetaServerToolCaller:`

                Tool invocation generated by a server-side tool.

              - `class BetaServerToolCaller20260120:`

          - `class BetaWebSearchToolResultBlock:`

            - `required BetaWebSearchToolResultBlockContent Content`

              - `class BetaWebSearchToolResultError:`

                - `required BetaWebSearchToolResultErrorCode ErrorCode`

                  - `"invalid_tool_input"InvalidToolInput`

                  - `"unavailable"Unavailable`

                  - `"max_uses_exceeded"MaxUsesExceeded`

                  - `"too_many_requests"TooManyRequests`

                  - `"query_too_long"QueryTooLong`

                  - `"request_too_large"RequestTooLarge`

                - `JsonElement Type "web_search_tool_result_error"constant`

              - `IReadOnlyList<BetaWebSearchResultBlock>`

                - `required string EncryptedContent`

                - `required string? PageAge`

                - `required string Title`

                - `JsonElement Type "web_search_result"constant`

                - `required string Url`

            - `required string ToolUseID`

            - `JsonElement Type "web_search_tool_result"constant`

            - `Caller Caller`

              Tool invocation directly from the model.

              - `class BetaDirectCaller:`

                Tool invocation directly from the model.

              - `class BetaServerToolCaller:`

                Tool invocation generated by a server-side tool.

              - `class BetaServerToolCaller20260120:`

          - `class BetaWebFetchToolResultBlock:`

            - `required Content Content`

              - `class BetaWebFetchToolResultErrorBlock:`

                - `required BetaWebFetchToolResultErrorCode ErrorCode`

                  - `"invalid_tool_input"InvalidToolInput`

                  - `"url_too_long"UrlTooLong`

                  - `"url_not_allowed"UrlNotAllowed`

                  - `"url_not_in_prior_context"UrlNotInPriorContext`

                  - `"url_not_accessible"UrlNotAccessible`

                  - `"unsupported_content_type"UnsupportedContentType`

                  - `"too_many_requests"TooManyRequests`

                  - `"max_uses_exceeded"MaxUsesExceeded`

                  - `"unavailable"Unavailable`

                - `JsonElement Type "web_fetch_tool_result_error"constant`

              - `class BetaWebFetchBlock:`

                - `required BetaDocumentBlock Content`

                  - `required BetaCitationConfig? Citations`

                    Citation configuration for the document

                    - `required Boolean Enabled`

                  - `required Source Source`

                    - `class BetaBase64PdfSource:`

                      - `required string Data`

                      - `JsonElement MediaType "application/pdf"constant`

                      - `JsonElement Type "base64"constant`

                    - `class BetaPlainTextSource:`

                      - `required string Data`

                      - `JsonElement MediaType "text/plain"constant`

                      - `JsonElement Type "text"constant`

                  - `required string? Title`

                    The title of the document

                  - `JsonElement Type "document"constant`

                - `required string? RetrievedAt`

                  ISO 8601 timestamp when the content was retrieved

                - `JsonElement Type "web_fetch_result"constant`

                - `required string Url`

                  Fetched content URL

            - `required string ToolUseID`

            - `JsonElement Type "web_fetch_tool_result"constant`

            - `Caller Caller`

              Tool invocation directly from the model.

              - `class BetaDirectCaller:`

                Tool invocation directly from the model.

              - `class BetaServerToolCaller:`

                Tool invocation generated by a server-side tool.

              - `class BetaServerToolCaller20260120:`

          - `class BetaAdvisorToolResultBlock:`

            - `required Content Content`

              - `class BetaAdvisorToolResultError:`

                - `required ErrorCode ErrorCode`

                  - `"max_uses_exceeded"MaxUsesExceeded`

                  - `"prompt_too_long"PromptTooLong`

                  - `"too_many_requests"TooManyRequests`

                  - `"overloaded"Overloaded`

                  - `"unavailable"Unavailable`

                  - `"execution_time_exceeded"ExecutionTimeExceeded`

                  - `"model_not_found"ModelNotFound`

                - `JsonElement Type "advisor_tool_result_error"constant`

              - `class BetaAdvisorResultBlock:`

                - `required string? StopReason`

                  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.

                - `required string Text`

                - `JsonElement Type "advisor_result"constant`

              - `class BetaAdvisorRedactedResultBlock:`

                - `required string EncryptedContent`

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

                - `required string? StopReason`

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

                - `JsonElement Type "advisor_redacted_result"constant`

            - `required string ToolUseID`

            - `JsonElement Type "advisor_tool_result"constant`

          - `class BetaCodeExecutionToolResultBlock:`

            - `required BetaCodeExecutionToolResultBlockContent Content`

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

              - `class BetaCodeExecutionToolResultError:`

                - `required BetaCodeExecutionToolResultErrorCode ErrorCode`

                  - `"invalid_tool_input"InvalidToolInput`

                  - `"unavailable"Unavailable`

                  - `"too_many_requests"TooManyRequests`

                  - `"execution_time_exceeded"ExecutionTimeExceeded`

                - `JsonElement Type "code_execution_tool_result_error"constant`

              - `class BetaCodeExecutionResultBlock:`

                - `required IReadOnlyList<BetaCodeExecutionOutputBlock> Content`

                  - `required string FileID`

                  - `JsonElement Type "code_execution_output"constant`

                - `required Long ReturnCode`

                - `required string Stderr`

                - `required string Stdout`

                - `JsonElement Type "code_execution_result"constant`

              - `class BetaEncryptedCodeExecutionResultBlock:`

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

                - `required IReadOnlyList<BetaCodeExecutionOutputBlock> Content`

                  - `required string FileID`

                  - `JsonElement Type "code_execution_output"constant`

                - `required string EncryptedStdout`

                - `required Long ReturnCode`

                - `required string Stderr`

                - `JsonElement Type "encrypted_code_execution_result"constant`

            - `required string ToolUseID`

            - `JsonElement Type "code_execution_tool_result"constant`

          - `class BetaBashCodeExecutionToolResultBlock:`

            - `required Content Content`

              - `class BetaBashCodeExecutionToolResultError:`

                - `required ErrorCode ErrorCode`

                  - `"invalid_tool_input"InvalidToolInput`

                  - `"unavailable"Unavailable`

                  - `"too_many_requests"TooManyRequests`

                  - `"execution_time_exceeded"ExecutionTimeExceeded`

                  - `"output_file_too_large"OutputFileTooLarge`

                - `JsonElement Type "bash_code_execution_tool_result_error"constant`

              - `class BetaBashCodeExecutionResultBlock:`

                - `required IReadOnlyList<BetaBashCodeExecutionOutputBlock> Content`

                  - `required string FileID`

                  - `JsonElement Type "bash_code_execution_output"constant`

                - `required Long ReturnCode`

                - `required string Stderr`

                - `required string Stdout`

                - `JsonElement Type "bash_code_execution_result"constant`

            - `required string ToolUseID`

            - `JsonElement Type "bash_code_execution_tool_result"constant`

          - `class BetaTextEditorCodeExecutionToolResultBlock:`

            - `required Content Content`

              - `class BetaTextEditorCodeExecutionToolResultError:`

                - `required ErrorCode ErrorCode`

                  - `"invalid_tool_input"InvalidToolInput`

                  - `"unavailable"Unavailable`

                  - `"too_many_requests"TooManyRequests`

                  - `"execution_time_exceeded"ExecutionTimeExceeded`

                  - `"file_not_found"FileNotFound`

                - `required string? ErrorMessage`

                - `JsonElement Type "text_editor_code_execution_tool_result_error"constant`

              - `class BetaTextEditorCodeExecutionViewResultBlock:`

                - `required string Content`

                - `required FileType FileType`

                  - `"text"Text`

                  - `"image"Image`

                  - `"pdf"Pdf`

                - `required Long? NumLines`

                - `required Long? StartLine`

                - `required Long? TotalLines`

                - `JsonElement Type "text_editor_code_execution_view_result"constant`

              - `class BetaTextEditorCodeExecutionCreateResultBlock:`

                - `required Boolean IsFileUpdate`

                - `JsonElement Type "text_editor_code_execution_create_result"constant`

              - `class BetaTextEditorCodeExecutionStrReplaceResultBlock:`

                - `required IReadOnlyList<string>? Lines`

                - `required Long? NewLines`

                - `required Long? NewStart`

                - `required Long? OldLines`

                - `required Long? OldStart`

                - `JsonElement Type "text_editor_code_execution_str_replace_result"constant`

            - `required string ToolUseID`

            - `JsonElement Type "text_editor_code_execution_tool_result"constant`

          - `class BetaToolSearchToolResultBlock:`

            - `required Content Content`

              - `class BetaToolSearchToolResultError:`

                - `required ErrorCode ErrorCode`

                  - `"invalid_tool_input"InvalidToolInput`

                  - `"unavailable"Unavailable`

                  - `"too_many_requests"TooManyRequests`

                  - `"execution_time_exceeded"ExecutionTimeExceeded`

                - `required string? ErrorMessage`

                - `JsonElement Type "tool_search_tool_result_error"constant`

              - `class BetaToolSearchToolSearchResultBlock:`

                - `required IReadOnlyList<BetaToolReferenceBlock> ToolReferences`

                  - `required string ToolName`

                  - `JsonElement Type "tool_reference"constant`

                - `JsonElement Type "tool_search_tool_search_result"constant`

            - `required string ToolUseID`

            - `JsonElement Type "tool_search_tool_result"constant`

          - `class BetaMcpToolUseBlock:`

            - `required string ID`

            - `required IReadOnlyDictionary<string, JsonElement> Input`

            - `required string Name`

              The name of the MCP tool

            - `required string ServerName`

              The name of the MCP server

            - `JsonElement Type "mcp_tool_use"constant`

          - `class BetaMcpToolResultBlock:`

            - `required Content Content`

              - `string`

              - `IReadOnlyList<BetaTextBlock>`

                - `required IReadOnlyList<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`.

                - `required string Text`

                - `JsonElement Type "text"constant`

            - `required Boolean IsError`

            - `required string ToolUseID`

            - `JsonElement Type "mcp_tool_result"constant`

          - `class BetaContainerUploadBlock:`

            Response model for a file uploaded to the container.

            - `required string FileID`

            - `JsonElement Type "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.

            - `required string? Content`

              Summary of compacted content, or null if compaction failed

            - `required string? EncryptedContent`

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

            - `JsonElement Type "compaction"constant`

          - `class BetaFallbackBlock:`

            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 routed directly by the sticky decision 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.

            - `required BetaFallbackInfo From`

              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.

              - `required Model Model`

                The model that will complete your prompt.

                See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.

                - `"claude-fable-5"ClaudeFable5`

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

                - `"claude-mythos-5"ClaudeMythos5`

                  Most capable model for cybersecurity and biology research

                - `"claude-opus-4-8"ClaudeOpus4_8`

                  Frontier intelligence for long-running agents and coding

                - `"claude-opus-4-7"ClaudeOpus4_7`

                  Frontier intelligence for long-running agents and coding

                - `"claude-mythos-preview"ClaudeMythosPreview`

                  New class of intelligence, strongest in coding and cybersecurity

                - `"claude-opus-4-6"ClaudeOpus4_6`

                  Frontier intelligence for long-running agents and coding

                - `"claude-sonnet-4-6"ClaudeSonnet4_6`

                  Best combination of speed and intelligence

                - `"claude-haiku-4-5"ClaudeHaiku4_5`

                  Fastest model with near-frontier intelligence

                - `"claude-haiku-4-5-20251001"ClaudeHaiku4_5_20251001`

                  Fastest model with near-frontier intelligence

                - `"claude-opus-4-5"ClaudeOpus4_5`

                  Premium model combining maximum intelligence with practical performance

                - `"claude-opus-4-5-20251101"ClaudeOpus4_5_20251101`

                  Premium model combining maximum intelligence with practical performance

                - `"claude-sonnet-4-5"ClaudeSonnet4_5`

                  High-performance model for agents and coding

                - `"claude-sonnet-4-5-20250929"ClaudeSonnet4_5_20250929`

                  High-performance model for agents and coding

                - `"claude-opus-4-1"ClaudeOpus4_1`

                  Exceptional model for specialized complex tasks

                - `"claude-opus-4-1-20250805"ClaudeOpus4_1_20250805`

                  Exceptional model for specialized complex tasks

                - `"claude-opus-4-0"ClaudeOpus4_0`

                  Powerful model for complex tasks

                - `"claude-opus-4-20250514"ClaudeOpus4_20250514`

                  Powerful model for complex tasks

                - `"claude-sonnet-4-0"ClaudeSonnet4_0`

                  High-performance model with extended thinking

                - `"claude-sonnet-4-20250514"ClaudeSonnet4_20250514`

                  High-performance model with extended thinking

                - `"claude-3-haiku-20240307"Claude_3_Haiku_20240307`

                  Fast and cost-effective model

            - `required BetaFallbackInfo To`

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

            - `JsonElement Type "fallback"constant`

        - `required BetaContextManagementResponse? ContextManagement`

          Context management response.

          Information about context management strategies applied during the request.

          - `required IReadOnlyList<AppliedEdit> AppliedEdits`

            List of context management edits that were applied.

            - `class BetaClearToolUses20250919EditResponse:`

              - `required Long ClearedInputTokens`

                Number of input tokens cleared by this edit.

              - `required Long ClearedToolUses`

                Number of tool uses that were cleared.

              - `JsonElement Type "clear_tool_uses_20250919"constant`

                The type of context management edit applied.

            - `class BetaClearThinking20251015EditResponse:`

              - `required Long ClearedInputTokens`

                Number of input tokens cleared by this edit.

              - `required Long ClearedThinkingTurns`

                Number of thinking turns that were cleared.

              - `JsonElement Type "clear_thinking_20251015"constant`

                The type of context management edit applied.

        - `required BetaDiagnostics? Diagnostics`

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

          - `required CacheMissReason? CacheMissReason`

            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.

            - `class BetaCacheMissModelChanged:`

              - `required Long CacheMissedInputTokens`

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

              - `JsonElement Type "model_changed"constant`

            - `class BetaCacheMissSystemChanged:`

              - `required Long CacheMissedInputTokens`

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

              - `JsonElement Type "system_changed"constant`

            - `class BetaCacheMissToolsChanged:`

              - `required Long CacheMissedInputTokens`

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

              - `JsonElement Type "tools_changed"constant`

            - `class BetaCacheMissMessagesChanged:`

              - `required Long CacheMissedInputTokens`

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

              - `JsonElement Type "messages_changed"constant`

            - `class BetaCacheMissPreviousMessageNotFound:`

              - `JsonElement Type "previous_message_not_found"constant`

            - `class BetaCacheMissUnavailable:`

              - `JsonElement Type "unavailable"constant`

        - `required Model Model`

          The model that will complete your prompt.

          See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.

        - `JsonElement Role "assistant"constant`

          Conversational role of the generated message.

          This will always be `"assistant"`.

        - `required BetaRefusalStopDetails? StopDetails`

          Structured information about a refusal.

          - `required Category? Category`

            The policy category that triggered the refusal.

            `null` when the refusal doesn't map to a named category.

            - `"cyber"Cyber`

            - `"bio"Bio`

            - `"reasoning_extraction"ReasoningExtraction`

          - `required string? Explanation`

            Human-readable explanation of the refusal.

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

          - `required string? FallbackCreditToken`

            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.

          - `required Boolean? FallbackHasPrefillClaim`

            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.

          - `required string? RecommendedModel`

            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.

          - `JsonElement Type "refusal"constant`

        - `required 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.

          - `"end_turn"EndTurn`

          - `"max_tokens"MaxTokens`

          - `"stop_sequence"StopSequence`

          - `"tool_use"ToolUse`

          - `"pause_turn"PauseTurn`

          - `"compaction"Compaction`

          - `"refusal"Refusal`

          - `"model_context_window_exceeded"ModelContextWindowExceeded`

        - `required 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.

        - `JsonElement Type "message"constant`

          Object type.

          For Messages, this is always `"message"`.

        - `required 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`.

          - `required BetaCacheCreation? CacheCreation`

            Breakdown of cached tokens by TTL

            - `required Long Ephemeral1hInputTokens`

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

            - `required Long Ephemeral5mInputTokens`

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

          - `required Long? CacheCreationInputTokens`

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

          - `required Long? CacheReadInputTokens`

            The number of input tokens read from the cache.

          - `required string? InferenceGeo`

            The geographic region where inference was performed for this request.

          - `required Long InputTokens`

            The number of input tokens which were used.

          - `required IReadOnlyList<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

            - `class BetaMessageIterationUsage:`

              Token usage for a sampling iteration.

              - `required BetaCacheCreation? CacheCreation`

                Breakdown of cached tokens by TTL

              - `required Long CacheCreationInputTokens`

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

              - `required Long CacheReadInputTokens`

                The number of input tokens read from the cache.

              - `required Long InputTokens`

                The number of input tokens which were used.

              - `required Model Model`

                The model that will complete your prompt.

                See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.

              - `required Long OutputTokens`

                The number of output tokens which were used.

              - `JsonElement Type "message"constant`

                Usage for a sampling iteration

            - `class BetaCompactionIterationUsage:`

              Token usage for a compaction iteration.

              - `required BetaCacheCreation? CacheCreation`

                Breakdown of cached tokens by TTL

              - `required Long CacheCreationInputTokens`

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

              - `required Long CacheReadInputTokens`

                The number of input tokens read from the cache.

              - `required Long InputTokens`

                The number of input tokens which were used.

              - `required Long OutputTokens`

                The number of output tokens which were used.

              - `JsonElement Type "compaction"constant`

                Usage for a compaction iteration

            - `class BetaAdvisorMessageIterationUsage:`

              Token usage for an advisor sub-inference iteration.

              - `required BetaCacheCreation? CacheCreation`

                Breakdown of cached tokens by TTL

              - `required Long CacheCreationInputTokens`

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

              - `required Long CacheReadInputTokens`

                The number of input tokens read from the cache.

              - `required Long InputTokens`

                The number of input tokens which were used.

              - `required Model Model`

                The model that will complete your prompt.

                See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.

              - `required Long OutputTokens`

                The number of output tokens which were used.

              - `JsonElement Type "advisor_message"constant`

                Usage for an advisor sub-inference iteration

            - `class BetaFallbackMessageIterationUsage:`

              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`.

              - `required BetaCacheCreation? CacheCreation`

                Breakdown of cached tokens by TTL

              - `required Long CacheCreationInputTokens`

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

              - `required Long CacheReadInputTokens`

                The number of input tokens read from the cache.

              - `required Long InputTokens`

                The number of input tokens which were used.

              - `required Model Model`

                The model that will complete your prompt.

                See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.

              - `required Long OutputTokens`

                The number of output tokens which were used.

              - `JsonElement Type "fallback_message"constant`

                Usage for the fallback-model attempt that served the response

          - `required Long OutputTokens`

            The number of output tokens which were used.

          - `required BetaOutputTokensDetails? OutputTokensDetails`

            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.

            - `required Long ThinkingTokens`

              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.

          - `required BetaServerToolUsage? ServerToolUse`

            The number of server tool requests.

            - `required Long WebFetchRequests`

              The number of web fetch tool requests.

            - `required Long WebSearchRequests`

              The number of web search tool requests.

          - `required ServiceTier? ServiceTier`

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

            - `"standard"Standard`

            - `"priority"Priority`

            - `"batch"Batch`

          - `required Speed? Speed`

            The inference speed mode used for this request.

            - `"standard"Standard`

            - `"fast"Fast`

      - `JsonElement Type "succeeded"constant`

    - `class BetaMessageBatchErroredResult:`

      - `required BetaErrorResponse Error`

        - `required BetaError Error`

          - `class BetaInvalidRequestError:`

            - `required string Message`

            - `JsonElement Type "invalid_request_error"constant`

          - `class BetaAuthenticationError:`

            - `required string Message`

            - `JsonElement Type "authentication_error"constant`

          - `class BetaBillingError:`

            - `required string Message`

            - `JsonElement Type "billing_error"constant`

          - `class BetaPermissionError:`

            - `required string Message`

            - `JsonElement Type "permission_error"constant`

          - `class BetaNotFoundError:`

            - `required string Message`

            - `JsonElement Type "not_found_error"constant`

          - `class BetaRateLimitError:`

            - `required string Message`

            - `JsonElement Type "rate_limit_error"constant`

          - `class BetaGatewayTimeoutError:`

            - `required string Message`

            - `JsonElement Type "timeout_error"constant`

          - `class BetaApiError:`

            - `required string Message`

            - `JsonElement Type "api_error"constant`

          - `class BetaOverloadedError:`

            - `required string Message`

            - `JsonElement Type "overloaded_error"constant`

        - `required string? RequestID`

        - `JsonElement Type "error"constant`

      - `JsonElement Type "errored"constant`

    - `class BetaMessageBatchCanceledResult:`

      - `JsonElement Type "canceled"constant`

    - `class BetaMessageBatchExpiredResult:`

      - `JsonElement Type "expired"constant`

### Example

```csharp
BatchResultsParams parameters = new() { MessageBatchID = "message_batch_id" };

await foreach (var betaMessageBatchIndividualResponse in client.Beta.Messages.Batches.ResultsStreaming(parameters))
{
    Console.WriteLine(betaMessageBatchIndividualResponse);
}
```