Retrieve Message Batch 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
ParametersExpand Collapse
ID of the Message Batch.
params: BatchResultsParams { betas }
betas?: Array<AnthropicBeta>Optional header to specify the beta version(s) you want to use.
Optional header to specify the beta version(s) you want to use.
"message-batches-2024-09-24" | "prompt-caching-2024-07-31" | "computer-use-2024-10-22" | 17 more
ReturnsExpand Collapse
BetaMessageBatchIndividualResponse { custom_id, result } This is a single line in the response .jsonl file and does not represent the response as a whole.
This is a single line in the response .jsonl file and does not represent the response as a whole.
custom_id: stringDeveloper-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.
Developer-provided ID created for each request in a Message Batch. Useful for matching results to requests, as results may be given out of request order.
Must be unique for each request within the Message Batch.
result: BetaMessageBatchResultProcessing result for this request.
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.
BetaMessageBatchSucceededResult { message, type }
message: BetaMessage { id, container, content, 7 more }
id: stringUnique object identifier.
Unique object identifier.
The format and length of IDs may change over time.
container: BetaContainer { id, expires_at, skills } | nullInformation about the container used in the request (for the code execution tool)
Information about the container used in the request (for the code execution tool)
Identifier for the container used in this request
The time at which the container will expire.
skills: Array<BetaSkill { skill_id, type, version } > | nullSkills loaded in the container
Skills loaded in the container
Skill ID
type: "anthropic" | "custom"Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
Skill version or 'latest' for most recent version
content: Array<BetaContentBlock>Content generated by the model.
Content generated by the model.
This is an array of content blocks, each of which has a type that determines its shape.
Example:
[{"type": "text", "text": "Hi, I'm Claude."}]
If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.
For example, if the input messages were:
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
Then the response content might be:
[{"type": "text", "text": "B)"}]
BetaTextBlock { citations, text, type }
citations: Array<BetaTextCitation> | nullCitations supporting the text block.
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.
BetaCitationCharLocation { cited_text, document_index, document_title, 4 more }
BetaCitationPageLocation { cited_text, document_index, document_title, 4 more }
BetaCitationContentBlockLocation { cited_text, document_index, document_title, 4 more }
BetaCitationsWebSearchResultLocation { cited_text, encrypted_index, title, 2 more }
BetaCitationSearchResultLocation { cited_text, end_block_index, search_result_index, 4 more }
BetaThinkingBlock { signature, thinking, type }
BetaRedactedThinkingBlock { data, type }
BetaToolUseBlock { id, input, name, 2 more }
caller?: BetaDirectCaller { type } | BetaServerToolCaller { tool_id, type } | BetaServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
BetaDirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
BetaServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
BetaServerToolCaller20260120 { tool_id, type }
BetaServerToolUseBlock { id, input, name, 2 more }
name: "web_search" | "web_fetch" | "code_execution" | 4 more
caller?: BetaDirectCaller { type } | BetaServerToolCaller { tool_id, type } | BetaServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
BetaDirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
BetaServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
BetaServerToolCaller20260120 { tool_id, type }
BetaWebSearchToolResultBlock { content, tool_use_id, type, caller }
content: BetaWebSearchToolResultBlockContent
BetaWebSearchToolResultError { error_code, type }
error_code: BetaWebSearchToolResultErrorCode
Array<BetaWebSearchResultBlock { encrypted_content, page_age, title, 2 more } >
caller?: BetaDirectCaller { type } | BetaServerToolCaller { tool_id, type } | BetaServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
BetaDirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
BetaServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
BetaServerToolCaller20260120 { tool_id, type }
BetaWebFetchToolResultBlock { content, tool_use_id, type, caller }
content: BetaWebFetchToolResultErrorBlock { error_code, type } | BetaWebFetchBlock { content, retrieved_at, type, url }
BetaWebFetchToolResultErrorBlock { error_code, type }
error_code: BetaWebFetchToolResultErrorCode
BetaWebFetchBlock { content, retrieved_at, type, url }
content: BetaDocumentBlock { citations, source, title, type }
citations: BetaCitationConfig { enabled } | nullCitation configuration for the document
Citation configuration for the document
source: BetaBase64PDFSource { data, media_type, type } | BetaPlainTextSource { data, media_type, type }
BetaBase64PDFSource { data, media_type, type }
BetaPlainTextSource { data, media_type, type }
The title of the document
ISO 8601 timestamp when the content was retrieved
Fetched content URL
caller?: BetaDirectCaller { type } | BetaServerToolCaller { tool_id, type } | BetaServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
BetaDirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
BetaServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
BetaServerToolCaller20260120 { tool_id, type }
BetaCodeExecutionToolResultBlock { content, tool_use_id, type }
Code execution result with encrypted stdout for PFC + web_search results.
Code execution result with encrypted stdout for PFC + web_search results.
BetaCodeExecutionToolResultError { error_code, type }
error_code: BetaCodeExecutionToolResultErrorCode
BetaCodeExecutionResultBlock { content, return_code, stderr, 2 more }
content: Array<BetaCodeExecutionOutputBlock { file_id, type } >
BetaEncryptedCodeExecutionResultBlock { content, encrypted_stdout, return_code, 2 more } Code execution result with encrypted stdout for PFC + web_search results.
Code execution result with encrypted stdout for PFC + web_search results.
content: Array<BetaCodeExecutionOutputBlock { file_id, type } >
BetaBashCodeExecutionToolResultBlock { content, tool_use_id, type }
content: BetaBashCodeExecutionToolResultError { error_code, type } | BetaBashCodeExecutionResultBlock { content, return_code, stderr, 2 more }
BetaBashCodeExecutionToolResultError { error_code, type }
error_code: "invalid_tool_input" | "unavailable" | "too_many_requests" | 2 more
BetaBashCodeExecutionResultBlock { content, return_code, stderr, 2 more }
content: Array<BetaBashCodeExecutionOutputBlock { file_id, type } >
BetaTextEditorCodeExecutionToolResultBlock { content, tool_use_id, type }
content: BetaTextEditorCodeExecutionToolResultError { error_code, error_message, type } | BetaTextEditorCodeExecutionViewResultBlock { content, file_type, num_lines, 3 more } | BetaTextEditorCodeExecutionCreateResultBlock { is_file_update, type } | BetaTextEditorCodeExecutionStrReplaceResultBlock { lines, new_lines, new_start, 3 more }
BetaTextEditorCodeExecutionToolResultError { error_code, error_message, type }
error_code: "invalid_tool_input" | "unavailable" | "too_many_requests" | 2 more
BetaTextEditorCodeExecutionViewResultBlock { content, file_type, num_lines, 3 more }
file_type: "text" | "image" | "pdf"
BetaTextEditorCodeExecutionCreateResultBlock { is_file_update, type }
BetaTextEditorCodeExecutionStrReplaceResultBlock { lines, new_lines, new_start, 3 more }
BetaToolSearchToolResultBlock { content, tool_use_id, type }
content: BetaToolSearchToolResultError { error_code, error_message, type } | BetaToolSearchToolSearchResultBlock { tool_references, type }
BetaToolSearchToolResultError { error_code, error_message, type }
error_code: "invalid_tool_input" | "unavailable" | "too_many_requests" | "execution_time_exceeded"
BetaToolSearchToolSearchResultBlock { tool_references, type }
tool_references: Array<BetaToolReferenceBlock { tool_name, type } >
BetaMCPToolUseBlock { id, input, name, 2 more }
The name of the MCP tool
The name of the MCP server
BetaMCPToolResultBlock { content, is_error, tool_use_id, type }
content: string | Array<BetaTextBlock { citations, text, type } >
Array<BetaTextBlock { citations, text, type } >
citations: Array<BetaTextCitation> | nullCitations supporting the text block.
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.
BetaCitationCharLocation { cited_text, document_index, document_title, 4 more }
BetaCitationPageLocation { cited_text, document_index, document_title, 4 more }
BetaCitationContentBlockLocation { cited_text, document_index, document_title, 4 more }
BetaCitationsWebSearchResultLocation { cited_text, encrypted_index, title, 2 more }
BetaCitationSearchResultLocation { cited_text, end_block_index, search_result_index, 4 more }
BetaContainerUploadBlock { file_id, type } Response model for a file uploaded to the container.
Response model for a file uploaded to the container.
BetaCompactionBlock { content, type } A compaction block returned when autocompact is triggered.
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.
Summary of compacted content, or null if compaction failed
context_management: BetaContextManagementResponse { applied_edits } | nullContext management response.
Context management response.
Information about context management strategies applied during the request.
applied_edits: Array<BetaClearToolUses20250919EditResponse { cleared_input_tokens, cleared_tool_uses, type } | BetaClearThinking20251015EditResponse { cleared_input_tokens, cleared_thinking_turns, type } >List of context management edits that were applied.
List of context management edits that were applied.
BetaClearToolUses20250919EditResponse { cleared_input_tokens, cleared_tool_uses, type }
Number of input tokens cleared by this edit.
Number of tool uses that were cleared.
The type of context management edit applied.
BetaClearThinking20251015EditResponse { cleared_input_tokens, cleared_thinking_turns, type }
Number of input tokens cleared by this edit.
Number of thinking turns that were cleared.
The type of context management edit applied.
model: ModelThe model that will complete your prompt.
The model that will complete your prompt.
See models for additional details and options.
"claude-opus-4-6" | "claude-sonnet-4-6" | "claude-opus-4-5-20251101" | 19 more
Most intelligent model for building agents and coding
Frontier intelligence at scale — built for coding, agents, and enterprise workflows
Premium model combining maximum intelligence with practical performance
Premium model combining maximum intelligence with practical performance
High-performance model with early extended thinking
High-performance model with early extended thinking
Fastest and most compact model for near-instant responsiveness
Our fastest model
Hybrid model, capable of near-instant responses and extended thinking
Hybrid model, capable of near-instant responses and extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
High-performance model with extended thinking
Our best model for real-world agents and coding
Our best model for real-world agents and coding
Our most capable model
Our most capable model
Our most capable model
Our most capable model
Excels at writing and complex tasks
Excels at writing and complex tasks
Our previous most fast and cost-effective
role: "assistant"Conversational role of the generated message.
Conversational role of the generated message.
This will always be "assistant".
stop_reason: BetaStopReason | nullThe reason that we stopped.
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 requestedmax_tokensor the model's maximum"stop_sequence": one of your provided customstop_sequenceswas 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.
stop_sequence: string | nullWhich custom stop sequence was generated, if any.
Which custom stop sequence was generated, if any.
This value will be a non-null string if one of your custom stop sequences was generated.
type: "message"Object type.
Object type.
For Messages, this is always "message".
usage: BetaUsage { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 7 more } Billing and rate-limit 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.
cache_creation: BetaCacheCreation { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens } | nullBreakdown of cached tokens by TTL
Breakdown of cached tokens by TTL
The number of input tokens used to create the 1 hour cache entry.
The number of input tokens used to create the 5 minute cache entry.
The number of input tokens used to create the cache entry.
The number of input tokens read from the cache.
The geographic region where inference was performed for this request.
The number of input tokens which were used.
iterations: BetaIterationsUsage | nullPer-iteration token usage breakdown.
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
BetaMessageIterationUsage { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 3 more } Token usage for a sampling iteration.
Token usage for a sampling iteration.
cache_creation: BetaCacheCreation { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens } | nullBreakdown of cached tokens by TTL
Breakdown of cached tokens by TTL
The number of input tokens used to create the 1 hour cache entry.
The number of input tokens used to create the 5 minute cache entry.
The number of input tokens used to create the cache entry.
The number of input tokens read from the cache.
The number of input tokens which were used.
The number of output tokens which were used.
Usage for a sampling iteration
BetaCompactionIterationUsage { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 3 more } Token usage for a compaction iteration.
Token usage for a compaction iteration.
cache_creation: BetaCacheCreation { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens } | nullBreakdown of cached tokens by TTL
Breakdown of cached tokens by TTL
The number of input tokens used to create the 1 hour cache entry.
The number of input tokens used to create the 5 minute cache entry.
The number of input tokens used to create the cache entry.
The number of input tokens read from the cache.
The number of input tokens which were used.
The number of output tokens which were used.
Usage for a compaction iteration
The number of output tokens which were used.
server_tool_use: BetaServerToolUsage { web_fetch_requests, web_search_requests } | nullThe number of server tool requests.
The number of server tool requests.
The number of web fetch tool requests.
The number of web search tool requests.
service_tier: "standard" | "priority" | "batch" | nullIf the request used the priority, standard, or batch tier.
If the request used the priority, standard, or batch tier.
speed: "standard" | "fast" | nullThe inference speed mode used for this request.
The inference speed mode used for this request.
BetaMessageBatchErroredResult { error, type }
error: BetaErrorResponse { error, request_id, type }
error: BetaError
BetaInvalidRequestError { message, type }
BetaAuthenticationError { message, type }
BetaBillingError { message, type }
BetaPermissionError { message, type }
BetaNotFoundError { message, type }
BetaRateLimitError { message, type }
BetaGatewayTimeoutError { message, type }
BetaAPIError { message, type }
BetaOverloadedError { message, type }
BetaMessageBatchCanceledResult { type }
BetaMessageBatchExpiredResult { type }
import Anthropic from '@anthropic-ai/sdk';
const client = new Anthropic({
apiKey: process.env['ANTHROPIC_API_KEY'], // This is the default and can be omitted
});
const betaMessageBatchIndividualResponse = await client.beta.messages.batches.results(
'message_batch_id',
);
console.log(betaMessageBatchIndividualResponse.custom_id);