Retrieve Message Batch results

messages().batches().resultsStreaming(, ) : MessageBatchIndividualResponse

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

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

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

Learn more about the Message Batches API in our user guide

ParametersExpand Collapse

params: BatchResultsParams

messageBatchId: Optional<String>

ID of the Message Batch.

ReturnsExpand Collapse

class MessageBatchIndividualResponse:

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

customId: String

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: MessageBatchResult

Processing result for this request.

Contains a Message output if processing was successful, an error response if processing failed, or the reason why processing was not attempted, such as cancellation or expiration.

Accepts one of the following:

class MessageBatchSucceededResult:

message: Message

id: String

Unique object identifier.

The format and length of IDs may change over time.

content: List<ContentBlock>

Content generated by the model.

This is an array of content blocks, each of which has a type that determines its shape.

Example:

[{"type": "text", "text": "Hi, I'm Claude."}]

If the request input messages ended with an assistant turn, then the response content will continue directly from that last turn. You can use this to constrain the model's output.

For example, if the input messages were:

[
  {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
  {"role": "assistant", "content": "The best answer is ("}
]

Then the response content might be:

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

Accepts one of the following:

class TextBlock:

citations: Optional<List<TextCitation>>

Citations supporting the text block.

The type of citation returned will depend on the type of document being cited. Citing a PDF results in page_location, plain text results in char_location, and content document results in content_block_location.

Accepts one of the following:

class CitationCharLocation:

citedText: String

documentIndex: Long

documentTitle: Optional<String>

endCharIndex: Long

fileId: Optional<String>

startCharIndex: Long

type: JsonValue;

Accepts one of the following:

CHAR_LOCATION("char_location")

class CitationPageLocation:

citedText: String

documentIndex: Long

documentTitle: Optional<String>

endPageNumber: Long

fileId: Optional<String>

startPageNumber: Long

type: JsonValue;

Accepts one of the following:

PAGE_LOCATION("page_location")

class CitationContentBlockLocation:

citedText: String

documentIndex: Long

documentTitle: Optional<String>

endBlockIndex: Long

fileId: Optional<String>

startBlockIndex: Long

type: JsonValue;

Accepts one of the following:

CONTENT_BLOCK_LOCATION("content_block_location")

class CitationsWebSearchResultLocation:

citedText: String

encryptedIndex: String

title: Optional<String>

type: JsonValue;

Accepts one of the following:

WEB_SEARCH_RESULT_LOCATION("web_search_result_location")

url: String

class CitationsSearchResultLocation:

citedText: String

endBlockIndex: Long

searchResultIndex: Long

source: String

startBlockIndex: Long

title: Optional<String>

type: JsonValue;

Accepts one of the following:

SEARCH_RESULT_LOCATION("search_result_location")

text: String

type: JsonValue;

Accepts one of the following:

TEXT("text")

class ThinkingBlock:

signature: String

thinking: String

type: JsonValue;

Accepts one of the following:

THINKING("thinking")

class RedactedThinkingBlock:

data: String

type: JsonValue;

Accepts one of the following:

REDACTED_THINKING("redacted_thinking")

class ToolUseBlock:

id: String

input: Input

name: String

type: JsonValue;

Accepts one of the following:

TOOL_USE("tool_use")

class ServerToolUseBlock:

id: String

input: Input

name: JsonValue;

Accepts one of the following:

WEB_SEARCH("web_search")

type: JsonValue;

Accepts one of the following:

SERVER_TOOL_USE("server_tool_use")

class WebSearchToolResultBlock:

content: WebSearchToolResultBlockContent

Accepts one of the following:

class WebSearchToolResultError:

errorCode: ErrorCode

Accepts one of the following:

INVALID_TOOL_INPUT("invalid_tool_input")

UNAVAILABLE("unavailable")

MAX_USES_EXCEEDED("max_uses_exceeded")

TOO_MANY_REQUESTS("too_many_requests")

QUERY_TOO_LONG("query_too_long")

type: JsonValue;

Accepts one of the following:

WEB_SEARCH_TOOL_RESULT_ERROR("web_search_tool_result_error")

List<WebSearchResultBlock>

encryptedContent: String

pageAge: Optional<String>

title: String

type: JsonValue;

Accepts one of the following:

WEB_SEARCH_RESULT("web_search_result")

url: String

toolUseId: String

type: JsonValue;

Accepts one of the following:

WEB_SEARCH_TOOL_RESULT("web_search_tool_result")

model: Model

The model that will complete your prompt.

See models for additional details and options.

Accepts one of the following:

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

Premium model combining maximum intelligence with practical performance

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

Premium model combining maximum intelligence with practical performance

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

High-performance model with early extended thinking

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

High-performance model with early extended thinking

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

Fastest and most compact model for near-instant responsiveness

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

Our fastest model

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

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

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

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

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

High-performance model with extended thinking

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

High-performance model with extended thinking

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

High-performance model with extended thinking

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

Our best model for real-world agents and coding

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

Our best model for real-world agents and coding

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

Our most capable model

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

Our most capable model

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

Our most capable model

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

Our most capable model

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

Excels at writing and complex tasks

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

Excels at writing and complex tasks

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

Our previous most fast and cost-effective

role: JsonValue;

Conversational role of the generated message.

This will always be "assistant".

Accepts one of the following:

ASSISTANT("assistant")

stopReason: Optional<StopReason>

The reason that we stopped.

This may be one the following values:

"end_turn": the model reached a natural stopping point
"max_tokens": we exceeded the requested max_tokens or the model's maximum
"stop_sequence": one of your provided custom stop_sequences was generated
"tool_use": the model invoked one or more tools
"pause_turn": we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue.
"refusal": when streaming classifiers intervene to handle potential policy violations

In non-streaming mode this value is always non-null. In streaming mode, it is null in the message_start event and non-null otherwise.

Accepts one of the following:

END_TURN("end_turn")

MAX_TOKENS("max_tokens")

STOP_SEQUENCE("stop_sequence")

TOOL_USE("tool_use")

PAUSE_TURN("pause_turn")

REFUSAL("refusal")

stopSequence: Optional<String>

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: JsonValue;

Object type.

For Messages, this is always "message".

Accepts one of the following:

MESSAGE("message")

usage: 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.

cacheCreation: Optional<CacheCreation>

Breakdown of cached tokens by TTL

ephemeral1hInputTokens: Long

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

minimum0

ephemeral5mInputTokens: Long

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

minimum0

cacheCreationInputTokens: Optional<Long>

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

minimum0

cacheReadInputTokens: Optional<Long>

The number of input tokens read from the cache.

minimum0

inputTokens: Long

The number of input tokens which were used.

minimum0

outputTokens: Long

The number of output tokens which were used.

minimum0

serverToolUse: Optional<ServerToolUsage>

The number of server tool requests.

webSearchRequests: Long

The number of web search tool requests.

minimum0

serviceTier: Optional<ServiceTier>

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

Accepts one of the following:

STANDARD("standard")

PRIORITY("priority")

BATCH("batch")

type: JsonValue;

Accepts one of the following:

SUCCEEDED("succeeded")

class MessageBatchErroredResult:

error: ErrorResponse

error: ErrorObject

Accepts one of the following:

class InvalidRequestError:

message: String

type: JsonValue;

Accepts one of the following:

INVALID_REQUEST_ERROR("invalid_request_error")

class AuthenticationError:

message: String

type: JsonValue;

Accepts one of the following:

AUTHENTICATION_ERROR("authentication_error")

class BillingError:

message: String

type: JsonValue;

Accepts one of the following:

BILLING_ERROR("billing_error")

class PermissionError:

message: String

type: JsonValue;

Accepts one of the following:

PERMISSION_ERROR("permission_error")

class NotFoundError:

message: String

type: JsonValue;

Accepts one of the following:

NOT_FOUND_ERROR("not_found_error")

class RateLimitError:

message: String

type: JsonValue;

Accepts one of the following:

RATE_LIMIT_ERROR("rate_limit_error")

class GatewayTimeoutError:

message: String

type: JsonValue;

Accepts one of the following:

TIMEOUT_ERROR("timeout_error")

class ApiErrorObject:

message: String

type: JsonValue;

Accepts one of the following:

API_ERROR("api_error")

class OverloadedError:

message: String

type: JsonValue;

Accepts one of the following:

OVERLOADED_ERROR("overloaded_error")

requestId: Optional<String>

type: JsonValue;

Accepts one of the following:

ERROR("error")

type: JsonValue;

Accepts one of the following:

ERRORED("errored")

class MessageBatchCanceledResult:

type: JsonValue;

Accepts one of the following:

CANCELED("canceled")

class MessageBatchExpiredResult:

type: JsonValue;

Accepts one of the following:

EXPIRED("expired")

Retrieve Message Batch results

package com.anthropic.example

import com.anthropic.client.AnthropicClient
import com.anthropic.client.okhttp.AnthropicOkHttpClient
import com.anthropic.core.http.StreamResponse
import com.anthropic.models.messages.batches.BatchResultsParams
import com.anthropic.models.messages.batches.MessageBatchIndividualResponse

fun main() {
    val client: AnthropicClient = AnthropicOkHttpClient.fromEnv()

    val messageBatchIndividualResponse: StreamResponse<MessageBatchIndividualResponse> = client.messages().batches().resultsStreaming("message_batch_id")
}

Returns Examples

package com.anthropic.example import com.anthropic.client.AnthropicClient import com.anthropic.client.okhttp.AnthropicOkHttpClient import com.anthropic.core.http.StreamResponse import com.anthropic.models.messages.batches.BatchResultsParams import com.anthropic.models.messages.batches.MessageBatchIndividualResponse fun main() { val client: AnthropicClient = AnthropicOkHttpClient.fromEnv() val messageBatchIndividualResponse: StreamResponse<MessageBatchIndividualResponse> = client.messages().batches().resultsStreaming("message_batch_id") }