> ## Documentation Index > Fetch the complete documentation index at: https://oma-codex-339-workspace-permissions.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Retrieve Message Batch results > Retrieve Message Batch results through the OMA API. Use `?beta=true` with `anthropic-beta: message-batches-2024-09-24` for the beta request and response shapes shown here. ## OpenAPI ````yaml /openapi/oma.en.json get /v1/messages/batches/{message_batch_id}/results openapi: 3.1.0 info: title: OMA API Reference version: 1.0.0 description: Open Managed Agents application API reference. servers: - url: http://localhost:38080 description: Local OMA server security: - omaApiKey: [] - omaBearer: [] paths: /v1/messages/batches/{message_batch_id}/results: get: summary: Retrieve Message Batch results description: >- 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 operationId: beta_message_batches_results parameters: - name: beta in: query required: true description: Selects the beta API contract for this endpoint. Must be `true`. schema: type: boolean enum: - true - name: message_batch_id in: path required: true schema: type: string description: ID of the Message Batch. title: Message Batch Id description: ID of the Message Batch. - name: anthropic-beta in: header required: true schema: type: string items: type: string description: >- Optional header to specify the beta version(s) you want to use. To use multiple betas, use a comma separated list like `beta1,beta2` or specify the header multiple times for each beta. title: Anthropic-Beta x-stainless-override-schema: x-stainless-param: betas x-stainless-extend-default: true type: array description: Optional header to specify the beta version(s) you want to use. items: $ref: '#/components/schemas/AnthropicBeta' x-default: message-batches-2024-09-24 description: >- Optional header to specify the beta version(s) you want to use. To use multiple betas, use a comma separated list like `beta1,beta2` or specify the header multiple times for each beta. - name: anthropic-version in: header required: false schema: type: string description: |- The version of the OMA API you want to use. Read more about versioning and our version history here. title: Anthropic-Version description: |- The version of the OMA API you want to use. Read more about versioning and our version history here. responses: '200': description: Successful Response content: application/x-jsonl: schema: $ref: '#/components/schemas/BetaMessageBatchIndividualResponse' 4XX: description: |- Error response. See our errors documentation for more details. content: application/json: schema: $ref: '#/components/schemas/BetaErrorResponse' components: schemas: BetaMessageBatchIndividualResponse: description: >- This is a single line in the response `.jsonl` file and does not represent the response as a whole. properties: custom_id: description: >- 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. examples: - my-custom-id-1 title: Custom Id type: string result: description: >- 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. discriminator: mapping: canceled: $ref: '#/components/schemas/BetaCanceledResult' errored: $ref: '#/components/schemas/BetaErroredResult' expired: $ref: '#/components/schemas/BetaExpiredResult' succeeded: $ref: '#/components/schemas/BetaSucceededResult' propertyName: type oneOf: - $ref: '#/components/schemas/BetaSucceededResult' - $ref: '#/components/schemas/BetaErroredResult' - $ref: '#/components/schemas/BetaCanceledResult' - $ref: '#/components/schemas/BetaExpiredResult' title: Result required: - custom_id - result title: MessageBatchIndividualResponse type: object BetaErrorResponse: properties: error: discriminator: mapping: api_error: $ref: '#/components/schemas/BetaAPIError' authentication_error: $ref: '#/components/schemas/BetaAuthenticationError' billing_error: $ref: '#/components/schemas/BetaBillingError' invalid_request_error: $ref: '#/components/schemas/BetaInvalidRequestError' not_found_error: $ref: '#/components/schemas/BetaNotFoundError' overloaded_error: $ref: '#/components/schemas/BetaOverloadedError' permission_error: $ref: '#/components/schemas/BetaPermissionError' rate_limit_error: $ref: '#/components/schemas/BetaRateLimitError' timeout_error: $ref: '#/components/schemas/BetaGatewayTimeoutError' propertyName: type oneOf: - $ref: '#/components/schemas/BetaInvalidRequestError' - $ref: '#/components/schemas/BetaAuthenticationError' - $ref: '#/components/schemas/BetaBillingError' - $ref: '#/components/schemas/BetaPermissionError' - $ref: '#/components/schemas/BetaNotFoundError' - $ref: '#/components/schemas/BetaRateLimitError' - $ref: '#/components/schemas/BetaGatewayTimeoutError' - $ref: '#/components/schemas/BetaAPIError' - $ref: '#/components/schemas/BetaOverloadedError' title: Error request_id: anyOf: - type: string - type: 'null' default: null title: Request Id type: const: error default: error title: Type type: string required: - error - request_id - type title: ErrorResponse type: object BetaCanceledResult: properties: type: const: canceled default: canceled title: Type type: string required: - type title: CanceledResult type: object BetaErroredResult: properties: error: $ref: '#/components/schemas/BetaErrorResponse' type: const: errored default: errored title: Type type: string required: - error - type title: ErroredResult type: object BetaExpiredResult: properties: type: const: expired default: expired title: Type type: string required: - type title: ExpiredResult type: object BetaSucceededResult: properties: message: $ref: '#/components/schemas/BetaMessage' type: const: succeeded default: succeeded title: Type type: string required: - message - type title: SucceededResult type: object BetaAPIError: properties: message: default: Internal server error title: Message type: string type: const: api_error default: api_error title: Type type: string required: - message - type title: APIError type: object BetaAuthenticationError: properties: message: default: Authentication error title: Message type: string type: const: authentication_error default: authentication_error title: Type type: string required: - message - type title: AuthenticationError type: object BetaBillingError: properties: message: default: Billing error title: Message type: string type: const: billing_error default: billing_error title: Type type: string required: - message - type title: BillingError type: object BetaInvalidRequestError: properties: message: default: Invalid request title: Message type: string type: const: invalid_request_error default: invalid_request_error title: Type type: string required: - message - type title: InvalidRequestError type: object BetaNotFoundError: properties: message: default: Not found title: Message type: string type: const: not_found_error default: not_found_error title: Type type: string required: - message - type title: NotFoundError type: object BetaOverloadedError: properties: message: default: Overloaded title: Message type: string type: const: overloaded_error default: overloaded_error title: Type type: string required: - message - type title: OverloadedError type: object BetaPermissionError: properties: message: default: Permission denied title: Message type: string type: const: permission_error default: permission_error title: Type type: string required: - message - type title: PermissionError type: object BetaRateLimitError: properties: message: default: Rate limited title: Message type: string type: const: rate_limit_error default: rate_limit_error title: Type type: string required: - message - type title: RateLimitError type: object BetaGatewayTimeoutError: properties: message: default: Request timeout title: Message type: string type: const: timeout_error default: timeout_error title: Type type: string required: - message - type title: GatewayTimeoutError type: object BetaMessage: examples: - content: - citations: null text: Hi! I am your AI assistant. type: text id: msg_013Zva2CMHLNnXjNJJKqJ2EF model: claude-opus-4-6 role: assistant stop_details: null stop_reason: end_turn stop_sequence: null type: message usage: input_tokens: 2095 output_tokens: 503 properties: id: description: |- Unique object identifier. The format and length of IDs may change over time. examples: - msg_013Zva2CMHLNnXjNJJKqJ2EF title: Id type: string type: const: message default: message description: |- Object type. For Messages, this is always `"message"`. title: Type type: string role: const: assistant default: assistant description: |- Conversational role of the generated message. This will always be `"assistant"`. title: Role type: string content: description: >- 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 the model."}] ``` 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)"}] ``` examples: - - citations: null text: Hi! I am your AI assistant. type: text items: $ref: '#/components/schemas/BetaContentBlock' title: Content type: array model: $ref: '#/components/schemas/Model' stop_reason: anyOf: - $ref: '#/components/schemas/BetaStopReason' - type: 'null' description: >- The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. title: Stop Reason stop_sequence: anyOf: - type: string - type: 'null' default: null description: >- 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. title: Stop Sequence stop_details: anyOf: - $ref: '#/components/schemas/BetaRefusalStopDetails' - type: 'null' default: null description: >- Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. usage: $ref: '#/components/schemas/BetaUsage' description: >- Billing and rate-limit usage. OMA'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 the model. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. examples: - input_tokens: 2095 output_tokens: 503 diagnostics: anyOf: - $ref: '#/components/schemas/BetaDiagnostics' - type: 'null' default: null description: >- Request-level diagnostics. Present only when `diagnostics` was supplied on the request; `null` when no prompt-cache divergence was detected. context_management: anyOf: - $ref: '#/components/schemas/BetaResponseContextManagement' - type: 'null' default: null description: >- Context management response. Information about context management strategies applied during the request. container: anyOf: - $ref: '#/components/schemas/BetaContainer' - type: 'null' default: null description: >- Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. required: - id - type - role - content - model - stop_reason - stop_sequence - stop_details - usage - diagnostics - context_management - container title: Message type: object x-stainless-python-custom-imports: - from .beta_content_block import BetaContentBlock as BetaContentBlock BetaContentBlock: discriminator: mapping: advisor_tool_result: $ref: '#/components/schemas/BetaResponseAdvisorToolResultBlock' bash_code_execution_tool_result: $ref: '#/components/schemas/BetaResponseBashCodeExecutionToolResultBlock' code_execution_tool_result: $ref: '#/components/schemas/BetaResponseCodeExecutionToolResultBlock' compaction: $ref: '#/components/schemas/BetaResponseCompactionBlock' container_upload: $ref: '#/components/schemas/BetaResponseContainerUploadBlock' fallback: $ref: '#/components/schemas/BetaResponseFallbackBlock' mcp_tool_result: $ref: '#/components/schemas/BetaResponseMCPToolResultBlock' mcp_tool_use: $ref: '#/components/schemas/BetaResponseMCPToolUseBlock' redacted_thinking: $ref: '#/components/schemas/BetaResponseRedactedThinkingBlock' server_tool_use: $ref: '#/components/schemas/BetaResponseServerToolUseBlock' text: $ref: '#/components/schemas/BetaResponseTextBlock' text_editor_code_execution_tool_result: $ref: >- #/components/schemas/BetaResponseTextEditorCodeExecutionToolResultBlock thinking: $ref: '#/components/schemas/BetaResponseThinkingBlock' tool_search_tool_result: $ref: '#/components/schemas/BetaResponseToolSearchToolResultBlock' tool_use: $ref: '#/components/schemas/BetaResponseToolUseBlock' web_fetch_tool_result: $ref: '#/components/schemas/BetaResponseWebFetchToolResultBlock' web_search_tool_result: $ref: '#/components/schemas/BetaResponseWebSearchToolResultBlock' propertyName: type oneOf: - $ref: '#/components/schemas/BetaResponseTextBlock' - $ref: '#/components/schemas/BetaResponseThinkingBlock' - $ref: '#/components/schemas/BetaResponseRedactedThinkingBlock' - $ref: '#/components/schemas/BetaResponseToolUseBlock' - $ref: '#/components/schemas/BetaResponseServerToolUseBlock' - $ref: '#/components/schemas/BetaResponseWebSearchToolResultBlock' - $ref: '#/components/schemas/BetaResponseWebFetchToolResultBlock' - $ref: '#/components/schemas/BetaResponseAdvisorToolResultBlock' - $ref: '#/components/schemas/BetaResponseCodeExecutionToolResultBlock' - $ref: '#/components/schemas/BetaResponseBashCodeExecutionToolResultBlock' - $ref: >- #/components/schemas/BetaResponseTextEditorCodeExecutionToolResultBlock - $ref: '#/components/schemas/BetaResponseToolSearchToolResultBlock' - $ref: '#/components/schemas/BetaResponseMCPToolUseBlock' - $ref: '#/components/schemas/BetaResponseMCPToolResultBlock' - $ref: '#/components/schemas/BetaResponseContainerUploadBlock' - $ref: '#/components/schemas/BetaResponseCompactionBlock' - $ref: '#/components/schemas/BetaResponseFallbackBlock' Model: title: Model description: |- The model that will complete your prompt. See models for additional details and options. anyOf: - type: string - const: claude-sonnet-5 description: High-performance model for coding and agents x-stainless-nominal: false - const: claude-fable-5 description: >- Next generation of intelligence for the hardest knowledge work and coding problems x-stainless-nominal: false - const: claude-mythos-5 description: Most capable model for cybersecurity and biology research x-stainless-nominal: false - const: claude-opus-5 description: Powerful intelligence for long-running agents and coding x-stainless-nominal: false - const: claude-opus-4-8 description: Powerful intelligence for long-running agents and coding x-stainless-nominal: false - const: claude-opus-4-7 description: Powerful intelligence for long-running agents and coding x-stainless-nominal: false - const: claude-mythos-preview description: New class of intelligence, strongest in coding and cybersecurity x-stainless-nominal: false deprecated: true x-stainless-deprecation-message: >- Reaches end of life on June 30, 2026. Please migrate to `claude-mythos-5`. - const: claude-opus-4-6 description: Powerful intelligence for long-running agents and coding x-stainless-nominal: false - const: claude-sonnet-4-6 description: Best combination of speed and intelligence x-stainless-nominal: false - const: claude-haiku-4-5 description: Fastest model with near-frontier intelligence x-stainless-nominal: false - const: claude-haiku-4-5-20251001 description: Fastest model with near-frontier intelligence x-stainless-nominal: false - const: claude-opus-4-5 description: Powerful intelligence for long-running agents and coding x-stainless-nominal: false - const: claude-opus-4-5-20251101 description: Powerful intelligence for long-running agents and coding x-stainless-nominal: false - const: claude-sonnet-4-5 description: High-performance model for agents and coding x-stainless-nominal: false - const: claude-sonnet-4-5-20250929 description: High-performance model for agents and coding x-stainless-nominal: false BetaStopReason: enum: - end_turn - max_tokens - stop_sequence - tool_use - pause_turn - compaction - refusal - model_context_window_exceeded type: string BetaRefusalStopDetails: description: Structured information about a refusal. properties: category: anyOf: - $ref: '#/components/schemas/BetaRefusalCategory' - type: 'null' default: null description: |- The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. explanation: anyOf: - type: string - type: 'null' default: null description: >- Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. examples: - >- This request was declined because it conflicts with the usage policy. title: Explanation fallback_credit_token: anyOf: - type: string - type: 'null' default: null description: >- 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. examples: - QW50aHJvcGljL0NsYXVkZQ== title: Fallback Credit Token fallback_has_prefill_claim: anyOf: - type: boolean - type: 'null' default: null description: >- 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. title: Fallback Has Prefill Claim recommended_model: anyOf: - type: string - type: 'null' default: null description: >- 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. examples: - claude-sonnet-4-6 title: Recommended Model type: const: refusal default: refusal title: Type type: string required: - category - explanation - fallback_credit_token - fallback_has_prefill_claim - recommended_model - type title: RefusalStopDetails type: object BetaUsage: properties: cache_creation: anyOf: - $ref: '#/components/schemas/BetaCacheCreation' - type: 'null' default: null description: Breakdown of cached tokens by TTL cache_creation_input_tokens: anyOf: - minimum: 0 type: integer - type: 'null' default: null description: The number of input tokens used to create the cache entry. examples: - 2051 title: Cache Creation Input Tokens cache_read_input_tokens: anyOf: - minimum: 0 type: integer - type: 'null' default: null description: The number of input tokens read from the cache. examples: - 2051 title: Cache Read Input Tokens fallback_credit: anyOf: - $ref: '#/components/schemas/BetaFallbackCreditUsage' - type: 'null' default: null description: >- Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). inference_geo: anyOf: - type: string - type: 'null' default: null description: >- The geographic region where inference was performed for this request. examples: - global title: Inference Geo input_tokens: description: The number of input tokens which were used. examples: - 2095 minimum: 0 title: Input Tokens type: integer iterations: $ref: '#/components/schemas/BetaIterationsUsage' output_tokens: description: The number of output tokens which were used. examples: - 503 minimum: 0 title: Output Tokens type: integer output_tokens_details: anyOf: - $ref: '#/components/schemas/BetaOutputTokensDetails' - type: 'null' default: null description: >- 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. server_tool_use: anyOf: - $ref: '#/components/schemas/BetaServerToolUsage' - type: 'null' default: null description: The number of server tool requests. service_tier: anyOf: - enum: - standard - priority - batch type: string - type: 'null' default: null description: If the request used the priority, standard, or batch tier. title: Service Tier speed: anyOf: - $ref: '#/components/schemas/BetaSpeed' - type: 'null' default: null description: The inference speed mode used for this request. required: - cache_creation - cache_creation_input_tokens - cache_read_input_tokens - fallback_credit - inference_geo - input_tokens - iterations - output_tokens - output_tokens_details - server_tool_use - service_tier - speed title: Usage type: object BetaDiagnostics: description: |- Response envelope for request-level diagnostics. Present (possibly null) whenever the caller supplied `diagnostics` on the request. properties: cache_miss_reason: anyOf: - discriminator: mapping: messages_changed: $ref: '#/components/schemas/BetaCacheMissMessagesChanged' model_changed: $ref: '#/components/schemas/BetaCacheMissModelChanged' previous_message_not_found: $ref: '#/components/schemas/BetaCacheMissPreviousMessageNotFound' system_changed: $ref: '#/components/schemas/BetaCacheMissSystemChanged' tools_changed: $ref: '#/components/schemas/BetaCacheMissToolsChanged' unavailable: $ref: '#/components/schemas/BetaCacheMissUnavailable' propertyName: type oneOf: - $ref: '#/components/schemas/BetaCacheMissModelChanged' - $ref: '#/components/schemas/BetaCacheMissSystemChanged' - $ref: '#/components/schemas/BetaCacheMissToolsChanged' - $ref: '#/components/schemas/BetaCacheMissMessagesChanged' - $ref: '#/components/schemas/BetaCacheMissPreviousMessageNotFound' - $ref: '#/components/schemas/BetaCacheMissUnavailable' - type: 'null' default: null description: >- 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. title: Cache Miss Reason required: - cache_miss_reason title: Diagnostics type: object BetaResponseContextManagement: properties: applied_edits: description: List of context management edits that were applied. items: discriminator: mapping: clear_thinking_20251015: $ref: '#/components/schemas/BetaResponseClearThinking20251015Edit' clear_tool_uses_20250919: $ref: '#/components/schemas/BetaResponseClearToolUses20250919Edit' propertyName: type oneOf: - $ref: '#/components/schemas/BetaResponseClearToolUses20250919Edit' - $ref: '#/components/schemas/BetaResponseClearThinking20251015Edit' title: Applied Edits type: array required: - applied_edits title: ResponseContextManagement type: object BetaContainer: description: >- Information about the container used in the request (for the code execution tool) properties: expires_at: description: The time at which the container will expire. format: date-time title: Expires At type: string id: description: Identifier for the container used in this request examples: - container_011CpZohnwH4vuy7gazohgSP title: Id type: string skills: anyOf: - items: $ref: '#/components/schemas/BetaSkill' type: array - type: 'null' default: null description: Skills loaded in the container title: Skills required: - expires_at - id - skills title: Container type: object BetaResponseAdvisorToolResultBlock: properties: content: anyOf: - $ref: '#/components/schemas/BetaResponseAdvisorToolResultError' - $ref: '#/components/schemas/BetaResponseAdvisorResultBlock' - $ref: '#/components/schemas/BetaResponseAdvisorRedactedResultBlock' title: Content tool_use_id: pattern: ^srvtoolu_[a-zA-Z0-9_]+$ title: Tool Use Id type: string type: const: advisor_tool_result default: advisor_tool_result title: Type type: string required: - content - tool_use_id - type title: ResponseAdvisorToolResultBlock type: object BetaResponseBashCodeExecutionToolResultBlock: properties: content: anyOf: - $ref: >- #/components/schemas/BetaResponseBashCodeExecutionToolResultError - $ref: '#/components/schemas/BetaResponseBashCodeExecutionResultBlock' title: Content tool_use_id: pattern: ^srvtoolu_[a-zA-Z0-9_]+$ title: Tool Use Id type: string type: const: bash_code_execution_tool_result default: bash_code_execution_tool_result title: Type type: string required: - content - tool_use_id - type title: ResponseBashCodeExecutionToolResultBlock type: object BetaResponseCodeExecutionToolResultBlock: properties: content: anyOf: - $ref: '#/components/schemas/BetaResponseCodeExecutionToolResultError' - $ref: '#/components/schemas/BetaResponseCodeExecutionResultBlock' - $ref: >- #/components/schemas/BetaResponseEncryptedCodeExecutionResultBlock title: Content tool_use_id: pattern: ^srvtoolu_[a-zA-Z0-9_]+$ title: Tool Use Id type: string type: const: code_execution_tool_result default: code_execution_tool_result title: Type type: string required: - content - tool_use_id - type title: ResponseCodeExecutionToolResultBlock type: object BetaResponseCompactionBlock: description: >- 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. properties: content: anyOf: - type: string - type: 'null' description: Summary of compacted content, or null if compaction failed title: Content encrypted_content: anyOf: - type: string - type: 'null' default: null description: Opaque metadata from prior compaction, to be round-tripped verbatim title: Encrypted Content type: const: compaction default: compaction title: Type type: string required: - content - encrypted_content - type title: ResponseCompactionBlock type: object BetaResponseContainerUploadBlock: description: Response model for a file uploaded to the container. properties: file_id: title: File Id type: string type: const: container_upload default: container_upload title: Type type: string required: - file_id - type title: ResponseContainerUploadBlock type: object BetaResponseFallbackBlock: description: >- Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. properties: from: $ref: '#/components/schemas/BetaResponseFallbackHopInfo' description: >- 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. to: $ref: '#/components/schemas/BetaResponseFallbackHopInfo' description: >- The fallback model producing the content that follows this block. Its `model` is always the canonical id. trigger: $ref: '#/components/schemas/BetaFallbackRefusalTrigger' description: What caused the `from` model to hand over at this hop. type: const: fallback default: fallback title: Type type: string required: - from - to - trigger - type title: ResponseFallbackBlock type: object BetaResponseMCPToolResultBlock: properties: content: anyOf: - type: string - items: $ref: '#/components/schemas/BetaResponseTextBlock' title: beta_mcp_tool_result_block_content_item type: array title: beta_mcp_tool_result_block_content title: Content is_error: default: false title: Is Error type: boolean tool_use_id: pattern: ^[a-zA-Z0-9_-]+$ title: Tool Use Id type: string type: const: mcp_tool_result default: mcp_tool_result title: Type type: string required: - content - is_error - tool_use_id - type title: ResponseMCPToolResultBlock type: object BetaResponseMCPToolUseBlock: properties: id: pattern: ^[a-zA-Z0-9_-]+$ title: Id type: string input: additionalProperties: true title: Input type: object name: description: The name of the MCP tool title: Name type: string server_name: description: The name of the MCP server title: Server Name type: string type: const: mcp_tool_use default: mcp_tool_use title: Type type: string required: - id - input - name - server_name - type title: ResponseMCPToolUseBlock type: object BetaResponseRedactedThinkingBlock: properties: data: description: >- The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See extended thinking for details. title: Data type: string type: const: redacted_thinking default: redacted_thinking title: Type type: string required: - data - type title: ResponseRedactedThinkingBlock type: object BetaResponseServerToolUseBlock: properties: caller: discriminator: mapping: code_execution_20250825: $ref: '#/components/schemas/BetaServerToolCaller' code_execution_20260120: $ref: '#/components/schemas/BetaServerToolCaller_20260120' direct: $ref: '#/components/schemas/BetaDirectCaller' propertyName: type oneOf: - $ref: '#/components/schemas/BetaDirectCaller' - $ref: '#/components/schemas/BetaServerToolCaller' - $ref: '#/components/schemas/BetaServerToolCaller_20260120' title: Caller id: pattern: ^srvtoolu_[a-zA-Z0-9_]+$ title: Id type: string input: additionalProperties: true title: Input type: object name: enum: - advisor - web_search - web_fetch - code_execution - bash_code_execution - text_editor_code_execution - tool_search_tool_regex - tool_search_tool_bm25 title: Name type: string type: const: server_tool_use default: server_tool_use title: Type type: string required: - id - input - name - type title: ResponseServerToolUseBlock type: object BetaResponseTextBlock: properties: citations: anyOf: - items: discriminator: mapping: char_location: $ref: '#/components/schemas/BetaResponseCharLocationCitation' content_block_location: $ref: >- #/components/schemas/BetaResponseContentBlockLocationCitation page_location: $ref: '#/components/schemas/BetaResponsePageLocationCitation' search_result_location: $ref: >- #/components/schemas/BetaResponseSearchResultLocationCitation web_search_result_location: $ref: >- #/components/schemas/BetaResponseWebSearchResultLocationCitation propertyName: type oneOf: - $ref: '#/components/schemas/BetaResponseCharLocationCitation' - $ref: '#/components/schemas/BetaResponsePageLocationCitation' - $ref: >- #/components/schemas/BetaResponseContentBlockLocationCitation - $ref: >- #/components/schemas/BetaResponseWebSearchResultLocationCitation - $ref: >- #/components/schemas/BetaResponseSearchResultLocationCitation type: array - type: 'null' default: null description: >- 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`. title: Citations text: maxLength: 5000000 minLength: 0 title: Text type: string type: const: text default: text title: Type type: string required: - citations - text - type title: ResponseTextBlock type: object BetaResponseTextEditorCodeExecutionToolResultBlock: properties: content: anyOf: - $ref: >- #/components/schemas/BetaResponseTextEditorCodeExecutionToolResultError - $ref: >- #/components/schemas/BetaResponseTextEditorCodeExecutionViewResultBlock - $ref: >- #/components/schemas/BetaResponseTextEditorCodeExecutionCreateResultBlock - $ref: >- #/components/schemas/BetaResponseTextEditorCodeExecutionStrReplaceResultBlock title: Content tool_use_id: pattern: ^srvtoolu_[a-zA-Z0-9_]+$ title: Tool Use Id type: string type: const: text_editor_code_execution_tool_result default: text_editor_code_execution_tool_result title: Type type: string required: - content - tool_use_id - type title: ResponseTextEditorCodeExecutionToolResultBlock type: object BetaResponseThinkingBlock: properties: signature: description: >- A value used to verify that this thinking block was generated by the model when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See extended thinking for details. title: Signature type: string thinking: description: The text of the model's thinking process for this block. title: Thinking type: string type: const: thinking default: thinking title: Type type: string required: - signature - thinking - type title: ResponseThinkingBlock type: object BetaResponseToolSearchToolResultBlock: properties: content: anyOf: - $ref: '#/components/schemas/BetaResponseToolSearchToolResultError' - $ref: '#/components/schemas/BetaResponseToolSearchToolSearchResultBlock' title: Content tool_use_id: pattern: ^srvtoolu_[a-zA-Z0-9_]+$ title: Tool Use Id type: string type: const: tool_search_tool_result default: tool_search_tool_result title: Type type: string required: - content - tool_use_id - type title: ResponseToolSearchToolResultBlock type: object BetaResponseToolUseBlock: properties: caller: discriminator: mapping: code_execution_20250825: $ref: '#/components/schemas/BetaServerToolCaller' code_execution_20260120: $ref: '#/components/schemas/BetaServerToolCaller_20260120' direct: $ref: '#/components/schemas/BetaDirectCaller' propertyName: type oneOf: - $ref: '#/components/schemas/BetaDirectCaller' - $ref: '#/components/schemas/BetaServerToolCaller' - $ref: '#/components/schemas/BetaServerToolCaller_20260120' title: Caller id: pattern: ^[a-zA-Z0-9_-]+$ title: Id type: string input: additionalProperties: true title: Input type: object name: minLength: 1 title: Name type: string type: const: tool_use default: tool_use title: Type type: string required: - id - input - name - type title: ResponseToolUseBlock type: object BetaResponseWebFetchToolResultBlock: properties: caller: discriminator: mapping: code_execution_20250825: $ref: '#/components/schemas/BetaServerToolCaller' code_execution_20260120: $ref: '#/components/schemas/BetaServerToolCaller_20260120' direct: $ref: '#/components/schemas/BetaDirectCaller' propertyName: type oneOf: - $ref: '#/components/schemas/BetaDirectCaller' - $ref: '#/components/schemas/BetaServerToolCaller' - $ref: '#/components/schemas/BetaServerToolCaller_20260120' title: Caller content: anyOf: - $ref: '#/components/schemas/BetaResponseWebFetchToolResultError' - $ref: '#/components/schemas/BetaResponseWebFetchResultBlock' title: Content tool_use_id: pattern: ^srvtoolu_[a-zA-Z0-9_]+$ title: Tool Use Id type: string type: const: web_fetch_tool_result default: web_fetch_tool_result title: Type type: string required: - content - tool_use_id - type title: ResponseWebFetchToolResultBlock type: object BetaResponseWebSearchToolResultBlock: properties: caller: discriminator: mapping: code_execution_20250825: $ref: '#/components/schemas/BetaServerToolCaller' code_execution_20260120: $ref: '#/components/schemas/BetaServerToolCaller_20260120' direct: $ref: '#/components/schemas/BetaDirectCaller' propertyName: type oneOf: - $ref: '#/components/schemas/BetaDirectCaller' - $ref: '#/components/schemas/BetaServerToolCaller' - $ref: '#/components/schemas/BetaServerToolCaller_20260120' title: Caller content: anyOf: - $ref: '#/components/schemas/BetaResponseWebSearchToolResultError' - items: $ref: '#/components/schemas/BetaResponseWebSearchResultBlock' type: array title: Content tool_use_id: pattern: ^srvtoolu_[a-zA-Z0-9_]+$ title: Tool Use Id type: string type: const: web_search_tool_result default: web_search_tool_result title: Type type: string required: - content - tool_use_id - type title: ResponseWebSearchToolResultBlock type: object BetaRefusalCategory: description: The policy category that triggered a refusal. enum: - cyber - bio - frontier_llm - reasoning_extraction - general_harms title: RefusalCategory type: string x-enum-descriptions: - >- The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - >- The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - >- The request was classified as assisting the development of competing AI models. Benign machine learning work can also trigger this category. - >- The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use adaptive thinking. - >- The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. BetaCacheCreation: properties: ephemeral_1h_input_tokens: default: 0 description: The number of input tokens used to create the 1 hour cache entry. minimum: 0 title: Ephemeral 1H Input Tokens type: integer ephemeral_5m_input_tokens: default: 0 description: The number of input tokens used to create the 5 minute cache entry. minimum: 0 title: Ephemeral 5M Input Tokens type: integer required: - ephemeral_1h_input_tokens - ephemeral_5m_input_tokens title: CacheCreation type: object BetaFallbackCreditUsage: description: Outcome of the ``fallback_credit_token`` presented on this request. properties: status: description: >- Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. discriminator: mapping: not_applied: $ref: '#/components/schemas/BetaFallbackCreditNotApplied' redeemed: $ref: '#/components/schemas/BetaFallbackCreditRedeemed' propertyName: type oneOf: - $ref: '#/components/schemas/BetaFallbackCreditRedeemed' - $ref: '#/components/schemas/BetaFallbackCreditNotApplied' title: Status required: - status title: FallbackCreditUsage type: object BetaIterationsUsage: anyOf: - items: discriminator: mapping: advisor_message: $ref: '#/components/schemas/BetaAdvisorMessageIterationUsage' compaction: $ref: '#/components/schemas/BetaCompactionIterationUsage' fallback_message: $ref: '#/components/schemas/BetaFallbackMessageIterationUsage' message: $ref: '#/components/schemas/BetaMessageIterationUsage' propertyName: type oneOf: - $ref: '#/components/schemas/BetaMessageIterationUsage' - $ref: '#/components/schemas/BetaCompactionIterationUsage' - $ref: '#/components/schemas/BetaAdvisorMessageIterationUsage' - $ref: '#/components/schemas/BetaFallbackMessageIterationUsage' x-stainless-naming: java: type_name: BetaIterationsUsageItems csharp: type_name: BetaIterationsUsageItems type: array - type: 'null' default: null description: >- 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 title: Iterations BetaOutputTokensDetails: properties: thinking_tokens: default: 0 description: >- 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. minimum: 0 title: Thinking Tokens type: integer required: - thinking_tokens title: OutputTokensDetails type: object BetaServerToolUsage: properties: web_fetch_requests: default: 0 description: The number of web fetch tool requests. examples: - 2 minimum: 0 title: Web Fetch Requests type: integer web_search_requests: default: 0 description: The number of web search tool requests. examples: - 0 minimum: 0 title: Web Search Requests type: integer required: - web_fetch_requests - web_search_requests title: ServerToolUsage type: object BetaSpeed: type: string description: >- Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Not all models support `fast`; invalid combinations are rejected at create time. enum: - standard - fast BetaCacheMissMessagesChanged: properties: cache_missed_input_tokens: description: >- Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. title: Cache Missed Input Tokens type: integer type: const: messages_changed default: messages_changed title: Type type: string required: - cache_missed_input_tokens - type title: CacheMissMessagesChanged type: object BetaCacheMissModelChanged: properties: cache_missed_input_tokens: description: >- Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. title: Cache Missed Input Tokens type: integer type: const: model_changed default: model_changed title: Type type: string required: - cache_missed_input_tokens - type title: CacheMissModelChanged type: object BetaCacheMissPreviousMessageNotFound: properties: type: const: previous_message_not_found default: previous_message_not_found title: Type type: string required: - type title: CacheMissPreviousMessageNotFound type: object BetaCacheMissSystemChanged: properties: cache_missed_input_tokens: description: >- Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. title: Cache Missed Input Tokens type: integer type: const: system_changed default: system_changed title: Type type: string required: - cache_missed_input_tokens - type title: CacheMissSystemChanged type: object BetaCacheMissToolsChanged: properties: cache_missed_input_tokens: description: >- Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. title: Cache Missed Input Tokens type: integer type: const: tools_changed default: tools_changed title: Type type: string required: - cache_missed_input_tokens - type title: CacheMissToolsChanged type: object BetaCacheMissUnavailable: properties: type: const: unavailable default: unavailable title: Type type: string required: - type title: CacheMissUnavailable type: object BetaResponseClearThinking20251015Edit: properties: cleared_input_tokens: description: Number of input tokens cleared by this edit. minimum: 0 title: Cleared Input Tokens type: integer cleared_thinking_turns: description: Number of thinking turns that were cleared. minimum: 0 title: Cleared Thinking Turns type: integer type: const: clear_thinking_20251015 default: clear_thinking_20251015 description: The type of context management edit applied. title: Type type: string required: - cleared_input_tokens - cleared_thinking_turns - type title: ResponseClearThinking20251015Edit type: object BetaResponseClearToolUses20250919Edit: properties: cleared_input_tokens: description: Number of input tokens cleared by this edit. minimum: 0 title: Cleared Input Tokens type: integer cleared_tool_uses: description: Number of tool uses that were cleared. minimum: 0 title: Cleared Tool Uses type: integer type: const: clear_tool_uses_20250919 default: clear_tool_uses_20250919 description: The type of context management edit applied. title: Type type: string required: - cleared_input_tokens - cleared_tool_uses - type title: ResponseClearToolUses20250919Edit type: object BetaSkill: description: A skill that was loaded in a container (response model). properties: skill_id: description: Skill ID examples: - pdf maxLength: 64 minLength: 1 title: Skill Id type: string type: description: >- Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) enum: - anthropic - custom examples: - anthropic title: Type type: string version: description: Skill version or 'latest' for most recent version examples: - latest maxLength: 64 minLength: 1 title: Version type: string required: - skill_id - type - version title: Skill type: object BetaResponseAdvisorToolResultError: properties: error_code: $ref: '#/components/schemas/BetaAdvisorToolResultErrorCode' type: const: advisor_tool_result_error default: advisor_tool_result_error title: Type type: string required: - error_code - type title: ResponseAdvisorToolResultError type: object BetaResponseAdvisorResultBlock: properties: stop_reason: anyOf: - type: string - type: 'null' default: null description: >- 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. title: Stop Reason text: title: Text type: string type: const: advisor_result default: advisor_result title: Type type: string required: - stop_reason - text - type title: ResponseAdvisorResultBlock type: object BetaResponseAdvisorRedactedResultBlock: properties: encrypted_content: description: >- Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. title: Encrypted Content type: string stop_reason: anyOf: - type: string - type: 'null' default: null description: >- The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). title: Stop Reason type: const: advisor_redacted_result default: advisor_redacted_result title: Type type: string required: - encrypted_content - stop_reason - type title: ResponseAdvisorRedactedResultBlock type: object BetaResponseBashCodeExecutionToolResultError: properties: error_code: $ref: '#/components/schemas/BetaBashCodeExecutionToolResultErrorCode' type: const: bash_code_execution_tool_result_error default: bash_code_execution_tool_result_error title: Type type: string required: - error_code - type title: ResponseBashCodeExecutionToolResultError type: object BetaResponseBashCodeExecutionResultBlock: properties: content: items: $ref: '#/components/schemas/BetaResponseBashCodeExecutionOutputBlock' title: Content type: array return_code: title: Return Code type: integer stderr: title: Stderr type: string stdout: title: Stdout type: string type: const: bash_code_execution_result default: bash_code_execution_result title: Type type: string required: - content - return_code - stderr - stdout - type title: ResponseBashCodeExecutionResultBlock type: object BetaResponseCodeExecutionToolResultError: properties: error_code: $ref: '#/components/schemas/BetaCodeExecutionToolResultErrorCode' type: const: code_execution_tool_result_error default: code_execution_tool_result_error title: Type type: string required: - error_code - type title: ResponseCodeExecutionToolResultError type: object BetaResponseCodeExecutionResultBlock: properties: content: items: $ref: '#/components/schemas/BetaResponseCodeExecutionOutputBlock' title: Content type: array return_code: title: Return Code type: integer stderr: title: Stderr type: string stdout: title: Stdout type: string type: const: code_execution_result default: code_execution_result title: Type type: string required: - content - return_code - stderr - stdout - type title: ResponseCodeExecutionResultBlock type: object BetaResponseEncryptedCodeExecutionResultBlock: description: >- Code execution result with encrypted stdout for PFC + web_search results. properties: content: items: $ref: '#/components/schemas/BetaResponseCodeExecutionOutputBlock' title: Content type: array encrypted_stdout: title: Encrypted Stdout type: string return_code: title: Return Code type: integer stderr: title: Stderr type: string type: const: encrypted_code_execution_result default: encrypted_code_execution_result title: Type type: string required: - content - encrypted_stdout - return_code - stderr - type title: ResponseEncryptedCodeExecutionResultBlock type: object BetaResponseFallbackHopInfo: description: Identifies one hop of a fallback transition. properties: model: $ref: '#/components/schemas/Model' required: - model title: ResponseFallbackHopInfo type: object BetaFallbackRefusalTrigger: description: The `from` model declined for policy reasons. properties: category: anyOf: - $ref: '#/components/schemas/BetaRefusalCategory' - type: 'null' default: null description: >- The policy category that triggered the `from` model's refusal at this hop. `null` when the refusal doesn't map to a named category. Same vocabulary as `stop_details.category`. x-stainless-naming: csharp: type_name: BetaFallbackRefusalTriggerCategory type: const: refusal default: refusal title: Type type: string required: - category - type title: FallbackRefusalTrigger type: object BetaServerToolCaller: additionalProperties: false description: Tool invocation generated by a server-side tool. properties: tool_id: pattern: ^srvtoolu_[a-zA-Z0-9_]+$ title: Tool Id type: string type: const: code_execution_20250825 title: Type type: string required: - tool_id - type title: ServerToolCaller type: object BetaServerToolCaller_20260120: additionalProperties: false properties: tool_id: pattern: ^srvtoolu_[a-zA-Z0-9_]+$ title: Tool Id type: string type: const: code_execution_20260120 title: Type type: string required: - tool_id - type title: ServerToolCaller_20260120 type: object BetaDirectCaller: additionalProperties: false description: Tool invocation directly from the model. properties: type: const: direct title: Type type: string required: - type title: DirectCaller type: object BetaResponseCharLocationCitation: properties: cited_text: examples: - The grass is green. The sky is blue. title: Cited Text type: string document_index: minimum: 0 title: Document Index type: integer document_title: anyOf: - type: string - type: 'null' examples: - My Document title: Document Title end_char_index: title: End Char Index type: integer file_id: anyOf: - type: string - type: 'null' default: null examples: - file_011CNha8iCJcU1wXNR6q4V8w title: File Id start_char_index: minimum: 0 title: Start Char Index type: integer type: const: char_location default: char_location title: Type type: string required: - cited_text - document_index - document_title - end_char_index - file_id - start_char_index - type title: ResponseCharLocationCitation type: object BetaResponseContentBlockLocationCitation: properties: cited_text: description: >- 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. examples: - The grass is green. The sky is blue. title: Cited Text type: string document_index: minimum: 0 title: Document Index type: integer document_title: anyOf: - type: string - type: 'null' examples: - My Document title: Document Title end_block_index: description: >- 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`. title: End Block Index type: integer file_id: anyOf: - type: string - type: 'null' default: null examples: - file_011CNha8iCJcU1wXNR6q4V8w title: File Id start_block_index: description: >- 0-based index of the first cited block in the source's `content` array. minimum: 0 title: Start Block Index type: integer type: const: content_block_location default: content_block_location title: Type type: string required: - cited_text - document_index - document_title - end_block_index - file_id - start_block_index - type title: ResponseContentBlockLocationCitation type: object BetaResponsePageLocationCitation: properties: cited_text: examples: - The grass is green. The sky is blue. title: Cited Text type: string document_index: minimum: 0 title: Document Index type: integer document_title: anyOf: - type: string - type: 'null' examples: - My Document title: Document Title end_page_number: title: End Page Number type: integer file_id: anyOf: - type: string - type: 'null' default: null examples: - file_011CNha8iCJcU1wXNR6q4V8w title: File Id start_page_number: minimum: 1 title: Start Page Number type: integer type: const: page_location default: page_location title: Type type: string required: - cited_text - document_index - document_title - end_page_number - file_id - start_page_number - type title: ResponsePageLocationCitation type: object BetaResponseSearchResultLocationCitation: properties: cited_text: description: >- 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. examples: - The grass is green. The sky is blue. title: Cited Text type: string end_block_index: description: >- 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`. title: End Block Index type: integer search_result_index: description: >- 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. minimum: 0 title: Search Result Index type: integer source: title: Source type: string start_block_index: description: >- 0-based index of the first cited block in the source's `content` array. minimum: 0 title: Start Block Index type: integer title: anyOf: - type: string - type: 'null' title: Title type: const: search_result_location default: search_result_location title: Type type: string required: - cited_text - end_block_index - search_result_index - source - start_block_index - title - type title: ResponseSearchResultLocationCitation type: object BetaResponseWebSearchResultLocationCitation: properties: cited_text: examples: - The grass is green. The sky is blue. title: Cited Text type: string encrypted_index: title: Encrypted Index type: string title: anyOf: - maxLength: 512 type: string - type: 'null' title: Title type: const: web_search_result_location default: web_search_result_location title: Type type: string url: title: Url type: string required: - cited_text - encrypted_index - title - type - url title: ResponseWebSearchResultLocationCitation type: object BetaResponseTextEditorCodeExecutionToolResultError: properties: error_code: $ref: '#/components/schemas/BetaTextEditorCodeExecutionToolResultErrorCode' error_message: anyOf: - type: string - type: 'null' default: null title: Error Message type: const: text_editor_code_execution_tool_result_error default: text_editor_code_execution_tool_result_error title: Type type: string required: - error_code - error_message - type title: ResponseTextEditorCodeExecutionToolResultError type: object BetaResponseTextEditorCodeExecutionViewResultBlock: properties: content: title: Content type: string file_type: enum: - text - image - pdf title: File Type type: string num_lines: anyOf: - type: integer - type: 'null' default: null title: Num Lines start_line: anyOf: - type: integer - type: 'null' default: null title: Start Line total_lines: anyOf: - type: integer - type: 'null' default: null title: Total Lines type: const: text_editor_code_execution_view_result default: text_editor_code_execution_view_result title: Type type: string required: - content - file_type - num_lines - start_line - total_lines - type title: ResponseTextEditorCodeExecutionViewResultBlock type: object BetaResponseTextEditorCodeExecutionCreateResultBlock: properties: is_file_update: title: Is File Update type: boolean type: const: text_editor_code_execution_create_result default: text_editor_code_execution_create_result title: Type type: string required: - is_file_update - type title: ResponseTextEditorCodeExecutionCreateResultBlock type: object BetaResponseTextEditorCodeExecutionStrReplaceResultBlock: properties: lines: anyOf: - items: type: string type: array - type: 'null' default: null title: Lines new_lines: anyOf: - type: integer - type: 'null' default: null title: New Lines new_start: anyOf: - type: integer - type: 'null' default: null title: New Start old_lines: anyOf: - type: integer - type: 'null' default: null title: Old Lines old_start: anyOf: - type: integer - type: 'null' default: null title: Old Start type: const: text_editor_code_execution_str_replace_result default: text_editor_code_execution_str_replace_result title: Type type: string required: - lines - new_lines - new_start - old_lines - old_start - type title: ResponseTextEditorCodeExecutionStrReplaceResultBlock type: object BetaResponseToolSearchToolResultError: properties: error_code: $ref: '#/components/schemas/BetaToolSearchToolResultErrorCode' error_message: anyOf: - type: string - type: 'null' default: null title: Error Message type: const: tool_search_tool_result_error default: tool_search_tool_result_error title: Type type: string required: - error_code - error_message - type title: ResponseToolSearchToolResultError type: object BetaResponseToolSearchToolSearchResultBlock: properties: tool_references: items: $ref: '#/components/schemas/BetaResponseToolReferenceBlock' title: Tool References type: array type: const: tool_search_tool_search_result default: tool_search_tool_search_result title: Type type: string required: - tool_references - type title: ResponseToolSearchToolSearchResultBlock type: object BetaResponseWebFetchToolResultError: properties: error_code: $ref: '#/components/schemas/BetaWebFetchToolResultErrorCode' type: const: web_fetch_tool_result_error default: web_fetch_tool_result_error title: Type type: string required: - error_code - type title: ResponseWebFetchToolResultError type: object BetaResponseWebFetchResultBlock: properties: content: $ref: '#/components/schemas/BetaResponseDocumentBlock' retrieved_at: anyOf: - type: string - type: 'null' default: null description: ISO 8601 timestamp when the content was retrieved title: Retrieved At type: const: web_fetch_result default: web_fetch_result title: Type type: string url: description: Fetched content URL title: Url type: string required: - content - retrieved_at - type - url title: ResponseWebFetchResultBlock type: object BetaResponseWebSearchToolResultError: properties: error_code: $ref: '#/components/schemas/BetaWebSearchToolResultErrorCode' type: const: web_search_tool_result_error default: web_search_tool_result_error title: Type type: string required: - error_code - type title: ResponseWebSearchToolResultError type: object BetaResponseWebSearchResultBlock: properties: encrypted_content: title: Encrypted Content type: string page_age: anyOf: - type: string - type: 'null' default: null title: Page Age title: title: Title type: string type: const: web_search_result default: web_search_result title: Type type: string url: title: Url type: string required: - encrypted_content - page_age - title - type - url title: ResponseWebSearchResultBlock type: object BetaFallbackCreditNotApplied: description: No reprice was applied; ``reason`` says why. properties: reason: description: >- Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. enum: - body_mismatch - continuation_excluded - continuation_only - expired - invalid_target_model - not_enabled - reprice_unavailable - temporarily_unavailable - variant_fields_present - wrong_organization - wrong_platform - wrong_workspace title: Reason type: string remove_to_redeem: anyOf: - items: type: string type: array - type: 'null' default: null description: >- Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. title: Remove To Redeem type: const: not_applied default: not_applied title: Type type: string required: - reason - type title: FallbackCreditNotApplied type: object BetaFallbackCreditRedeemed: description: |- The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. properties: type: const: redeemed default: redeemed title: Type type: string required: - type title: FallbackCreditRedeemed type: object BetaAdvisorMessageIterationUsage: description: Token usage for an advisor sub-inference iteration. properties: cache_creation: anyOf: - $ref: '#/components/schemas/BetaCacheCreation' - type: 'null' default: null description: Breakdown of cached tokens by TTL cache_creation_input_tokens: default: 0 description: The number of input tokens used to create the cache entry. minimum: 0 title: Cache Creation Input Tokens type: integer cache_read_input_tokens: default: 0 description: The number of input tokens read from the cache. minimum: 0 title: Cache Read Input Tokens type: integer input_tokens: description: The number of input tokens which were used. minimum: 0 title: Input Tokens type: integer model: $ref: '#/components/schemas/Model' output_tokens: description: The number of output tokens which were used. minimum: 0 title: Output Tokens type: integer type: const: advisor_message default: advisor_message description: Usage for an advisor sub-inference iteration title: Type type: string required: - cache_creation - cache_creation_input_tokens - cache_read_input_tokens - input_tokens - model - output_tokens - type title: AdvisorMessageIterationUsage type: object BetaCompactionIterationUsage: description: Token usage for a compaction iteration. properties: cache_creation: anyOf: - $ref: '#/components/schemas/BetaCacheCreation' - type: 'null' default: null description: Breakdown of cached tokens by TTL cache_creation_input_tokens: default: 0 description: The number of input tokens used to create the cache entry. minimum: 0 title: Cache Creation Input Tokens type: integer cache_read_input_tokens: default: 0 description: The number of input tokens read from the cache. minimum: 0 title: Cache Read Input Tokens type: integer input_tokens: description: The number of input tokens which were used. minimum: 0 title: Input Tokens type: integer output_tokens: description: The number of output tokens which were used. minimum: 0 title: Output Tokens type: integer type: const: compaction default: compaction description: Usage for a compaction iteration title: Type type: string required: - cache_creation - cache_creation_input_tokens - cache_read_input_tokens - input_tokens - output_tokens - type title: CompactionIterationUsage type: object BetaFallbackMessageIterationUsage: description: >- 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`. properties: cache_creation: anyOf: - $ref: '#/components/schemas/BetaCacheCreation' - type: 'null' default: null description: Breakdown of cached tokens by TTL cache_creation_input_tokens: default: 0 description: The number of input tokens used to create the cache entry. minimum: 0 title: Cache Creation Input Tokens type: integer cache_read_input_tokens: default: 0 description: The number of input tokens read from the cache. minimum: 0 title: Cache Read Input Tokens type: integer input_tokens: description: The number of input tokens which were used. minimum: 0 title: Input Tokens type: integer model: $ref: '#/components/schemas/Model' output_tokens: description: The number of output tokens which were used. minimum: 0 title: Output Tokens type: integer type: const: fallback_message default: fallback_message description: Usage for the fallback-model attempt that served the response title: Type type: string required: - cache_creation - cache_creation_input_tokens - cache_read_input_tokens - input_tokens - model - output_tokens - type title: FallbackMessageIterationUsage type: object BetaMessageIterationUsage: description: Token usage for a sampling iteration. properties: cache_creation: anyOf: - $ref: '#/components/schemas/BetaCacheCreation' - type: 'null' default: null description: Breakdown of cached tokens by TTL cache_creation_input_tokens: default: 0 description: The number of input tokens used to create the cache entry. minimum: 0 title: Cache Creation Input Tokens type: integer cache_read_input_tokens: default: 0 description: The number of input tokens read from the cache. minimum: 0 title: Cache Read Input Tokens type: integer input_tokens: description: The number of input tokens which were used. minimum: 0 title: Input Tokens type: integer model: $ref: '#/components/schemas/Model' output_tokens: description: The number of output tokens which were used. minimum: 0 title: Output Tokens type: integer type: const: message default: message description: Usage for a sampling iteration title: Type type: string required: - cache_creation - cache_creation_input_tokens - cache_read_input_tokens - input_tokens - model - output_tokens - type title: MessageIterationUsage type: object BetaAdvisorToolResultErrorCode: enum: - max_uses_exceeded - prompt_too_long - too_many_requests - overloaded - unavailable - execution_time_exceeded - model_not_found title: AdvisorToolResultErrorCode type: string BetaBashCodeExecutionToolResultErrorCode: enum: - invalid_tool_input - unavailable - too_many_requests - execution_time_exceeded - output_file_too_large title: BashCodeExecutionToolResultErrorCode type: string BetaResponseBashCodeExecutionOutputBlock: properties: file_id: title: File Id type: string type: const: bash_code_execution_output default: bash_code_execution_output title: Type type: string required: - file_id - type title: ResponseBashCodeExecutionOutputBlock type: object BetaCodeExecutionToolResultErrorCode: enum: - invalid_tool_input - unavailable - too_many_requests - execution_time_exceeded title: CodeExecutionToolResultErrorCode type: string BetaResponseCodeExecutionOutputBlock: properties: file_id: title: File Id type: string type: const: code_execution_output default: code_execution_output title: Type type: string required: - file_id - type title: ResponseCodeExecutionOutputBlock type: object BetaTextEditorCodeExecutionToolResultErrorCode: enum: - invalid_tool_input - unavailable - too_many_requests - execution_time_exceeded - file_not_found title: TextEditorCodeExecutionToolResultErrorCode type: string BetaToolSearchToolResultErrorCode: enum: - invalid_tool_input - unavailable - too_many_requests - execution_time_exceeded title: ToolSearchToolResultErrorCode type: string BetaResponseToolReferenceBlock: properties: tool_name: maxLength: 256 minLength: 1 pattern: ^[a-zA-Z0-9_-]{1,256}$ title: Tool Name type: string type: const: tool_reference default: tool_reference title: Type type: string required: - tool_name - type title: ResponseToolReferenceBlock type: object BetaWebFetchToolResultErrorCode: enum: - invalid_tool_input - url_too_long - url_not_allowed - url_not_in_prior_context - url_not_accessible - unsupported_content_type - too_many_requests - max_uses_exceeded - unavailable title: WebFetchToolResultErrorCode type: string BetaResponseDocumentBlock: properties: citations: anyOf: - $ref: '#/components/schemas/BetaResponseCitationsConfig' - type: 'null' default: null description: Citation configuration for the document source: discriminator: mapping: base64: $ref: '#/components/schemas/BetaBase64PDFSource' text: $ref: '#/components/schemas/BetaPlainTextSource' propertyName: type oneOf: - $ref: '#/components/schemas/BetaBase64PDFSource' - $ref: '#/components/schemas/BetaPlainTextSource' title: Source title: anyOf: - type: string - type: 'null' default: null description: The title of the document title: Title type: const: document default: document title: Type type: string required: - citations - source - title - type title: ResponseDocumentBlock type: object BetaWebSearchToolResultErrorCode: enum: - invalid_tool_input - unavailable - max_uses_exceeded - too_many_requests - query_too_long - request_too_large title: WebSearchToolResultErrorCode type: string BetaResponseCitationsConfig: properties: enabled: default: false title: Enabled type: boolean required: - enabled title: ResponseCitationsConfig type: object BetaBase64PDFSource: additionalProperties: false properties: data: format: byte title: Data type: string media_type: const: application/pdf title: Media Type type: string type: const: base64 title: Type type: string required: - data - media_type - type title: Base64PDFSource type: object BetaPlainTextSource: additionalProperties: false properties: data: title: Data type: string media_type: const: text/plain title: Media Type type: string type: const: text title: Type type: string required: - data - media_type - type title: PlainTextSource type: object securitySchemes: omaApiKey: type: apiKey in: header name: X-Api-Key description: OMA workspace API key. x-default: sk-ant-local-default omaBearer: type: http scheme: bearer description: OMA workspace API key sent as a bearer token. ````