Batches
Create a Message Batch
Retrieve a Message Batch
List Message Batches
Cancel a Message Batch
Delete a Message Batch
Retrieve Message Batch results
ModelsExpand Collapse
class DeletedMessageBatch { id, type }
ID of the Message Batch.
type: :message_batch_deletedDeleted object type.
Deleted object type.
For Message Batches, this is always "message_batch_deleted".
class MessageBatch { id, archived_at, cancel_initiated_at, 7 more }
id: StringUnique object identifier.
Unique object identifier.
The format and length of IDs may change over time.
RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable.
RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated.
RFC 3339 datetime string representing the time at which the Message Batch was created.
ended_at: TimeRFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends.
RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends.
Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired.
RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation.
processing_status: :in_progress | :canceling | :endedProcessing status of the Message Batch.
Processing status of the Message Batch.
request_counts: MessageBatchRequestCounts { canceled, errored, expired, 2 more } Tallies requests within the Message Batch, categorized by their status.
Tallies requests within the Message Batch, categorized by their status.
Requests start as processing and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch.
canceled: IntegerNumber of requests in the Message Batch that have been canceled.
Number of requests in the Message Batch that have been canceled.
This is zero until processing of the entire Message Batch has ended.
errored: IntegerNumber of requests in the Message Batch that encountered an error.
Number of requests in the Message Batch that encountered an error.
This is zero until processing of the entire Message Batch has ended.
expired: IntegerNumber of requests in the Message Batch that have expired.
Number of requests in the Message Batch that have expired.
This is zero until processing of the entire Message Batch has ended.
Number of requests in the Message Batch that are processing.
succeeded: IntegerNumber of requests in the Message Batch that have completed successfully.
Number of requests in the Message Batch that have completed successfully.
This is zero until processing of the entire Message Batch has ended.
results_url: StringURL to a .jsonl file containing the results of the Message Batch requests. Specified only once processing ends.
URL to a .jsonl file containing the results of the Message Batch requests. Specified only once processing ends.
Results in the file are not guaranteed to be in the same order as requests. Use the custom_id field to match results to requests.
type: :message_batchObject type.
Object type.
For Message Batches, this is always "message_batch".
class MessageBatchCanceledResult { type }
class MessageBatchErroredResult { error, type }
error: ErrorResponse { error, request_id, type }
error: ErrorObject
class InvalidRequestError { message, type }
class AuthenticationError { message, type }
class BillingError { message, type }
class PermissionError { message, type }
class NotFoundError { message, type }
class RateLimitError { message, type }
class GatewayTimeoutError { message, type }
class APIErrorObject { message, type }
class OverloadedError { message, type }
class MessageBatchExpiredResult { type }
class MessageBatchIndividualResponse { 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: MessageBatchResultProcessing 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.
class MessageBatchSucceededResult { message, type }
message: Message { id, container, content, 6 more }
id: StringUnique object identifier.
Unique object identifier.
The format and length of IDs may change over time.
container: Container { id, expires_at } Information 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.
content: Array[ContentBlock]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)"}]
class TextBlock { citations, text, type }
citations: Array[TextCitation]Citations 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.
class CitationCharLocation { cited_text, document_index, document_title, 4 more }
class CitationPageLocation { cited_text, document_index, document_title, 4 more }
class CitationContentBlockLocation { cited_text, document_index, document_title, 4 more }
class CitationsWebSearchResultLocation { cited_text, encrypted_index, title, 2 more }
class CitationsSearchResultLocation { cited_text, end_block_index, search_result_index, 4 more }
class ThinkingBlock { signature, thinking, type }
class RedactedThinkingBlock { data, type }
class ToolUseBlock { id, caller_, input, 2 more }
caller_: DirectCaller { type } | ServerToolCaller { tool_id, type } | ServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
class DirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
class ServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
class ServerToolCaller20260120 { tool_id, type }
class ServerToolUseBlock { id, caller_, input, 2 more }
caller_: DirectCaller { type } | ServerToolCaller { tool_id, type } | ServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
class DirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
class ServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
class ServerToolCaller20260120 { tool_id, type }
name: :web_search | :web_fetch | :code_execution | 4 more
class WebSearchToolResultBlock { caller_, content, tool_use_id, type }
caller_: DirectCaller { type } | ServerToolCaller { tool_id, type } | ServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
class DirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
class ServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
class ServerToolCaller20260120 { tool_id, type }
content: WebSearchToolResultBlockContent
class WebSearchToolResultError { error_code, type }
error_code: WebSearchToolResultErrorCode
Array[WebSearchResultBlock { encrypted_content, page_age, title, 2 more } ]
class WebFetchToolResultBlock { caller_, content, tool_use_id, type }
caller_: DirectCaller { type } | ServerToolCaller { tool_id, type } | ServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
class DirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
class ServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
class ServerToolCaller20260120 { tool_id, type }
content: WebFetchToolResultErrorBlock { error_code, type } | WebFetchBlock { content, retrieved_at, type, url }
class WebFetchToolResultErrorBlock { error_code, type }
error_code: WebFetchToolResultErrorCode
class WebFetchBlock { content, retrieved_at, type, url }
content: DocumentBlock { citations, source, title, type }
citations: CitationsConfig { enabled } Citation configuration for the document
Citation configuration for the document
source: Base64PDFSource { data, media_type, type } | PlainTextSource { data, media_type, type }
class Base64PDFSource { data, media_type, type }
class PlainTextSource { data, media_type, type }
The title of the document
ISO 8601 timestamp when the content was retrieved
Fetched content URL
class CodeExecutionToolResultBlock { content, tool_use_id, type }
content: CodeExecutionToolResultBlockContentCode execution result with encrypted stdout for PFC + web_search results.
Code execution result with encrypted stdout for PFC + web_search results.
class CodeExecutionToolResultError { error_code, type }
error_code: CodeExecutionToolResultErrorCode
class CodeExecutionResultBlock { content, return_code, stderr, 2 more }
content: Array[CodeExecutionOutputBlock { file_id, type } ]
class EncryptedCodeExecutionResultBlock { 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[CodeExecutionOutputBlock { file_id, type } ]
class BashCodeExecutionToolResultBlock { content, tool_use_id, type }
content: BashCodeExecutionToolResultError { error_code, type } | BashCodeExecutionResultBlock { content, return_code, stderr, 2 more }
class BashCodeExecutionToolResultError { error_code, type }
error_code: BashCodeExecutionToolResultErrorCode
class BashCodeExecutionResultBlock { content, return_code, stderr, 2 more }
content: Array[BashCodeExecutionOutputBlock { file_id, type } ]
class TextEditorCodeExecutionToolResultBlock { content, tool_use_id, type }
content: TextEditorCodeExecutionToolResultError { error_code, error_message, type } | TextEditorCodeExecutionViewResultBlock { content, file_type, num_lines, 3 more } | TextEditorCodeExecutionCreateResultBlock { is_file_update, type } | TextEditorCodeExecutionStrReplaceResultBlock { lines, new_lines, new_start, 3 more }
class TextEditorCodeExecutionToolResultError { error_code, error_message, type }
error_code: TextEditorCodeExecutionToolResultErrorCode
class TextEditorCodeExecutionViewResultBlock { content, file_type, num_lines, 3 more }
file_type: :text | :image | :pdf
class TextEditorCodeExecutionCreateResultBlock { is_file_update, type }
class TextEditorCodeExecutionStrReplaceResultBlock { lines, new_lines, new_start, 3 more }
class ToolSearchToolResultBlock { content, tool_use_id, type }
content: ToolSearchToolResultError { error_code, error_message, type } | ToolSearchToolSearchResultBlock { tool_references, type }
class ToolSearchToolResultError { error_code, error_message, type }
error_code: ToolSearchToolResultErrorCode
class ToolSearchToolSearchResultBlock { tool_references, type }
tool_references: Array[ToolReferenceBlock { tool_name, type } ]
class ContainerUploadBlock { file_id, type } Response model for a file uploaded to the container.
Response model for a file uploaded to the container.
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 moreThe model that will complete your prompt.
The model that will complete your prompt.
See models for additional details and options.
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: :assistantConversational role of the generated message.
Conversational role of the generated message.
This will always be "assistant".
stop_reason: StopReasonThe 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: StringWhich 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: :messageObject type.
Object type.
For Messages, this is always "message".
usage: Usage { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 5 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: CacheCreation { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens } Breakdown 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.
The number of output tokens which were used.
server_tool_use: ServerToolUsage { web_fetch_requests, web_search_requests } The 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 | :batchIf the request used the priority, standard, or batch tier.
If the request used the priority, standard, or batch tier.
class MessageBatchErroredResult { error, type }
error: ErrorResponse { error, request_id, type }
error: ErrorObject
class InvalidRequestError { message, type }
class AuthenticationError { message, type }
class BillingError { message, type }
class PermissionError { message, type }
class NotFoundError { message, type }
class RateLimitError { message, type }
class GatewayTimeoutError { message, type }
class APIErrorObject { message, type }
class OverloadedError { message, type }
class MessageBatchCanceledResult { type }
class MessageBatchExpiredResult { type }
class MessageBatchRequestCounts { canceled, errored, expired, 2 more }
canceled: IntegerNumber of requests in the Message Batch that have been canceled.
Number of requests in the Message Batch that have been canceled.
This is zero until processing of the entire Message Batch has ended.
errored: IntegerNumber of requests in the Message Batch that encountered an error.
Number of requests in the Message Batch that encountered an error.
This is zero until processing of the entire Message Batch has ended.
expired: IntegerNumber of requests in the Message Batch that have expired.
Number of requests in the Message Batch that have expired.
This is zero until processing of the entire Message Batch has ended.
Number of requests in the Message Batch that are processing.
succeeded: IntegerNumber of requests in the Message Batch that have completed successfully.
Number of requests in the Message Batch that have completed successfully.
This is zero until processing of the entire Message Batch has ended.
MessageBatchResult = MessageBatchSucceededResult { message, type } | MessageBatchErroredResult { error, type } | MessageBatchCanceledResult { type } | MessageBatchExpiredResult { type } Processing 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.
class MessageBatchSucceededResult { message, type }
message: Message { id, container, content, 6 more }
id: StringUnique object identifier.
Unique object identifier.
The format and length of IDs may change over time.
container: Container { id, expires_at } Information 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.
content: Array[ContentBlock]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)"}]
class TextBlock { citations, text, type }
citations: Array[TextCitation]Citations 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.
class CitationCharLocation { cited_text, document_index, document_title, 4 more }
class CitationPageLocation { cited_text, document_index, document_title, 4 more }
class CitationContentBlockLocation { cited_text, document_index, document_title, 4 more }
class CitationsWebSearchResultLocation { cited_text, encrypted_index, title, 2 more }
class CitationsSearchResultLocation { cited_text, end_block_index, search_result_index, 4 more }
class ThinkingBlock { signature, thinking, type }
class RedactedThinkingBlock { data, type }
class ToolUseBlock { id, caller_, input, 2 more }
caller_: DirectCaller { type } | ServerToolCaller { tool_id, type } | ServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
class DirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
class ServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
class ServerToolCaller20260120 { tool_id, type }
class ServerToolUseBlock { id, caller_, input, 2 more }
caller_: DirectCaller { type } | ServerToolCaller { tool_id, type } | ServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
class DirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
class ServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
class ServerToolCaller20260120 { tool_id, type }
name: :web_search | :web_fetch | :code_execution | 4 more
class WebSearchToolResultBlock { caller_, content, tool_use_id, type }
caller_: DirectCaller { type } | ServerToolCaller { tool_id, type } | ServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
class DirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
class ServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
class ServerToolCaller20260120 { tool_id, type }
content: WebSearchToolResultBlockContent
class WebSearchToolResultError { error_code, type }
error_code: WebSearchToolResultErrorCode
Array[WebSearchResultBlock { encrypted_content, page_age, title, 2 more } ]
class WebFetchToolResultBlock { caller_, content, tool_use_id, type }
caller_: DirectCaller { type } | ServerToolCaller { tool_id, type } | ServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
class DirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
class ServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
class ServerToolCaller20260120 { tool_id, type }
content: WebFetchToolResultErrorBlock { error_code, type } | WebFetchBlock { content, retrieved_at, type, url }
class WebFetchToolResultErrorBlock { error_code, type }
error_code: WebFetchToolResultErrorCode
class WebFetchBlock { content, retrieved_at, type, url }
content: DocumentBlock { citations, source, title, type }
citations: CitationsConfig { enabled } Citation configuration for the document
Citation configuration for the document
source: Base64PDFSource { data, media_type, type } | PlainTextSource { data, media_type, type }
class Base64PDFSource { data, media_type, type }
class PlainTextSource { data, media_type, type }
The title of the document
ISO 8601 timestamp when the content was retrieved
Fetched content URL
class CodeExecutionToolResultBlock { content, tool_use_id, type }
content: CodeExecutionToolResultBlockContentCode execution result with encrypted stdout for PFC + web_search results.
Code execution result with encrypted stdout for PFC + web_search results.
class CodeExecutionToolResultError { error_code, type }
error_code: CodeExecutionToolResultErrorCode
class CodeExecutionResultBlock { content, return_code, stderr, 2 more }
content: Array[CodeExecutionOutputBlock { file_id, type } ]
class EncryptedCodeExecutionResultBlock { 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[CodeExecutionOutputBlock { file_id, type } ]
class BashCodeExecutionToolResultBlock { content, tool_use_id, type }
content: BashCodeExecutionToolResultError { error_code, type } | BashCodeExecutionResultBlock { content, return_code, stderr, 2 more }
class BashCodeExecutionToolResultError { error_code, type }
error_code: BashCodeExecutionToolResultErrorCode
class BashCodeExecutionResultBlock { content, return_code, stderr, 2 more }
content: Array[BashCodeExecutionOutputBlock { file_id, type } ]
class TextEditorCodeExecutionToolResultBlock { content, tool_use_id, type }
content: TextEditorCodeExecutionToolResultError { error_code, error_message, type } | TextEditorCodeExecutionViewResultBlock { content, file_type, num_lines, 3 more } | TextEditorCodeExecutionCreateResultBlock { is_file_update, type } | TextEditorCodeExecutionStrReplaceResultBlock { lines, new_lines, new_start, 3 more }
class TextEditorCodeExecutionToolResultError { error_code, error_message, type }
error_code: TextEditorCodeExecutionToolResultErrorCode
class TextEditorCodeExecutionViewResultBlock { content, file_type, num_lines, 3 more }
file_type: :text | :image | :pdf
class TextEditorCodeExecutionCreateResultBlock { is_file_update, type }
class TextEditorCodeExecutionStrReplaceResultBlock { lines, new_lines, new_start, 3 more }
class ToolSearchToolResultBlock { content, tool_use_id, type }
content: ToolSearchToolResultError { error_code, error_message, type } | ToolSearchToolSearchResultBlock { tool_references, type }
class ToolSearchToolResultError { error_code, error_message, type }
error_code: ToolSearchToolResultErrorCode
class ToolSearchToolSearchResultBlock { tool_references, type }
tool_references: Array[ToolReferenceBlock { tool_name, type } ]
class ContainerUploadBlock { file_id, type } Response model for a file uploaded to the container.
Response model for a file uploaded to the container.
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 moreThe model that will complete your prompt.
The model that will complete your prompt.
See models for additional details and options.
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: :assistantConversational role of the generated message.
Conversational role of the generated message.
This will always be "assistant".
stop_reason: StopReasonThe 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: StringWhich 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: :messageObject type.
Object type.
For Messages, this is always "message".
usage: Usage { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 5 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: CacheCreation { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens } Breakdown 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.
The number of output tokens which were used.
server_tool_use: ServerToolUsage { web_fetch_requests, web_search_requests } The 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 | :batchIf the request used the priority, standard, or batch tier.
If the request used the priority, standard, or batch tier.
class MessageBatchErroredResult { error, type }
error: ErrorResponse { error, request_id, type }
error: ErrorObject
class InvalidRequestError { message, type }
class AuthenticationError { message, type }
class BillingError { message, type }
class PermissionError { message, type }
class NotFoundError { message, type }
class RateLimitError { message, type }
class GatewayTimeoutError { message, type }
class APIErrorObject { message, type }
class OverloadedError { message, type }
class MessageBatchCanceledResult { type }
class MessageBatchExpiredResult { type }
class MessageBatchSucceededResult { message, type }
message: Message { id, container, content, 6 more }
id: StringUnique object identifier.
Unique object identifier.
The format and length of IDs may change over time.
container: Container { id, expires_at } Information 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.
content: Array[ContentBlock]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)"}]
class TextBlock { citations, text, type }
citations: Array[TextCitation]Citations 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.
class CitationCharLocation { cited_text, document_index, document_title, 4 more }
class CitationPageLocation { cited_text, document_index, document_title, 4 more }
class CitationContentBlockLocation { cited_text, document_index, document_title, 4 more }
class CitationsWebSearchResultLocation { cited_text, encrypted_index, title, 2 more }
class CitationsSearchResultLocation { cited_text, end_block_index, search_result_index, 4 more }
class ThinkingBlock { signature, thinking, type }
class RedactedThinkingBlock { data, type }
class ToolUseBlock { id, caller_, input, 2 more }
caller_: DirectCaller { type } | ServerToolCaller { tool_id, type } | ServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
class DirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
class ServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
class ServerToolCaller20260120 { tool_id, type }
class ServerToolUseBlock { id, caller_, input, 2 more }
caller_: DirectCaller { type } | ServerToolCaller { tool_id, type } | ServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
class DirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
class ServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
class ServerToolCaller20260120 { tool_id, type }
name: :web_search | :web_fetch | :code_execution | 4 more
class WebSearchToolResultBlock { caller_, content, tool_use_id, type }
caller_: DirectCaller { type } | ServerToolCaller { tool_id, type } | ServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
class DirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
class ServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
class ServerToolCaller20260120 { tool_id, type }
content: WebSearchToolResultBlockContent
class WebSearchToolResultError { error_code, type }
error_code: WebSearchToolResultErrorCode
Array[WebSearchResultBlock { encrypted_content, page_age, title, 2 more } ]
class WebFetchToolResultBlock { caller_, content, tool_use_id, type }
caller_: DirectCaller { type } | ServerToolCaller { tool_id, type } | ServerToolCaller20260120 { tool_id, type } Tool invocation directly from the model.
Tool invocation directly from the model.
class DirectCaller { type } Tool invocation directly from the model.
Tool invocation directly from the model.
class ServerToolCaller { tool_id, type } Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
class ServerToolCaller20260120 { tool_id, type }
content: WebFetchToolResultErrorBlock { error_code, type } | WebFetchBlock { content, retrieved_at, type, url }
class WebFetchToolResultErrorBlock { error_code, type }
error_code: WebFetchToolResultErrorCode
class WebFetchBlock { content, retrieved_at, type, url }
content: DocumentBlock { citations, source, title, type }
citations: CitationsConfig { enabled } Citation configuration for the document
Citation configuration for the document
source: Base64PDFSource { data, media_type, type } | PlainTextSource { data, media_type, type }
class Base64PDFSource { data, media_type, type }
class PlainTextSource { data, media_type, type }
The title of the document
ISO 8601 timestamp when the content was retrieved
Fetched content URL
class CodeExecutionToolResultBlock { content, tool_use_id, type }
content: CodeExecutionToolResultBlockContentCode execution result with encrypted stdout for PFC + web_search results.
Code execution result with encrypted stdout for PFC + web_search results.
class CodeExecutionToolResultError { error_code, type }
error_code: CodeExecutionToolResultErrorCode
class CodeExecutionResultBlock { content, return_code, stderr, 2 more }
content: Array[CodeExecutionOutputBlock { file_id, type } ]
class EncryptedCodeExecutionResultBlock { 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[CodeExecutionOutputBlock { file_id, type } ]
class BashCodeExecutionToolResultBlock { content, tool_use_id, type }
content: BashCodeExecutionToolResultError { error_code, type } | BashCodeExecutionResultBlock { content, return_code, stderr, 2 more }
class BashCodeExecutionToolResultError { error_code, type }
error_code: BashCodeExecutionToolResultErrorCode
class BashCodeExecutionResultBlock { content, return_code, stderr, 2 more }
content: Array[BashCodeExecutionOutputBlock { file_id, type } ]
class TextEditorCodeExecutionToolResultBlock { content, tool_use_id, type }
content: TextEditorCodeExecutionToolResultError { error_code, error_message, type } | TextEditorCodeExecutionViewResultBlock { content, file_type, num_lines, 3 more } | TextEditorCodeExecutionCreateResultBlock { is_file_update, type } | TextEditorCodeExecutionStrReplaceResultBlock { lines, new_lines, new_start, 3 more }
class TextEditorCodeExecutionToolResultError { error_code, error_message, type }
error_code: TextEditorCodeExecutionToolResultErrorCode
class TextEditorCodeExecutionViewResultBlock { content, file_type, num_lines, 3 more }
file_type: :text | :image | :pdf
class TextEditorCodeExecutionCreateResultBlock { is_file_update, type }
class TextEditorCodeExecutionStrReplaceResultBlock { lines, new_lines, new_start, 3 more }
class ToolSearchToolResultBlock { content, tool_use_id, type }
content: ToolSearchToolResultError { error_code, error_message, type } | ToolSearchToolSearchResultBlock { tool_references, type }
class ToolSearchToolResultError { error_code, error_message, type }
error_code: ToolSearchToolResultErrorCode
class ToolSearchToolSearchResultBlock { tool_references, type }
tool_references: Array[ToolReferenceBlock { tool_name, type } ]
class ContainerUploadBlock { file_id, type } Response model for a file uploaded to the container.
Response model for a file uploaded to the container.
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 moreThe model that will complete your prompt.
The model that will complete your prompt.
See models for additional details and options.
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: :assistantConversational role of the generated message.
Conversational role of the generated message.
This will always be "assistant".
stop_reason: StopReasonThe 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: StringWhich 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: :messageObject type.
Object type.
For Messages, this is always "message".
usage: Usage { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 5 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: CacheCreation { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens } Breakdown 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.
The number of output tokens which were used.
server_tool_use: ServerToolUsage { web_fetch_requests, web_search_requests } The 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 | :batchIf the request used the priority, standard, or batch tier.
If the request used the priority, standard, or batch tier.