Retrieve Message Batch results

client.Messages.Batches.Results(ctx, messageBatchID) (*MessageBatchIndividualResponse, error)

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

messageBatchID string

ID of the Message Batch.

ReturnsExpand Collapse

type MessageBatchIndividualResponse struct{…}

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 MessageBatchResultUnion

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:

type MessageBatchSucceededResult struct{…}

Message Message

ID string

Unique object identifier.

The format and length of IDs may change over time.

Content []ContentBlockUnion

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:

type TextBlock struct{…}

Citations []TextCitationUnion

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:

type CitationCharLocation struct{…}

CitedText string

DocumentIndex int64

DocumentTitle string

EndCharIndex int64

FileID string

StartCharIndex int64

Type CharLocation

Accepts one of the following:

const CharLocationCharLocation CharLocation = "char_location"

type CitationPageLocation struct{…}

CitedText string

DocumentIndex int64

DocumentTitle string

EndPageNumber int64

FileID string

StartPageNumber int64

Type PageLocation

Accepts one of the following:

const PageLocationPageLocation PageLocation = "page_location"

type CitationContentBlockLocation struct{…}

CitedText string

DocumentIndex int64

DocumentTitle string

EndBlockIndex int64

FileID string

StartBlockIndex int64

Type ContentBlockLocation

Accepts one of the following:

const ContentBlockLocationContentBlockLocation ContentBlockLocation = "content_block_location"

type CitationsWebSearchResultLocation struct{…}

CitedText string

EncryptedIndex string

Title string

Type WebSearchResultLocation

Accepts one of the following:

const WebSearchResultLocationWebSearchResultLocation WebSearchResultLocation = "web_search_result_location"

URL string

type CitationsSearchResultLocation struct{…}

CitedText string

EndBlockIndex int64

SearchResultIndex int64

Source string

StartBlockIndex int64

Title string

Type SearchResultLocation

Accepts one of the following:

const SearchResultLocationSearchResultLocation SearchResultLocation = "search_result_location"

Text string

Type Text

Accepts one of the following:

const TextText Text = "text"

type ThinkingBlock struct{…}

Signature string

Thinking string

Type Thinking

Accepts one of the following:

const ThinkingThinking Thinking = "thinking"

type RedactedThinkingBlock struct{…}

Data string

Type RedactedThinking

Accepts one of the following:

const RedactedThinkingRedactedThinking RedactedThinking = "redacted_thinking"

type ToolUseBlock struct{…}

ID string

Input map[string, any]

Name string

Type ToolUse

Accepts one of the following:

const ToolUseToolUse ToolUse = "tool_use"

type ServerToolUseBlock struct{…}

ID string

Input map[string, any]

Name WebSearch

Accepts one of the following:

const WebSearchWebSearch WebSearch = "web_search"

Type ServerToolUse

Accepts one of the following:

const ServerToolUseServerToolUse ServerToolUse = "server_tool_use"

type WebSearchToolResultBlock struct{…}

Content WebSearchToolResultBlockContentUnion

Accepts one of the following:

type WebSearchToolResultError struct{…}

ErrorCode WebSearchToolResultErrorErrorCode

Accepts one of the following:

const WebSearchToolResultErrorErrorCodeInvalidToolInput WebSearchToolResultErrorErrorCode = "invalid_tool_input"

const WebSearchToolResultErrorErrorCodeUnavailable WebSearchToolResultErrorErrorCode = "unavailable"

const WebSearchToolResultErrorErrorCodeMaxUsesExceeded WebSearchToolResultErrorErrorCode = "max_uses_exceeded"

const WebSearchToolResultErrorErrorCodeTooManyRequests WebSearchToolResultErrorErrorCode = "too_many_requests"

const WebSearchToolResultErrorErrorCodeQueryTooLong WebSearchToolResultErrorErrorCode = "query_too_long"

Type WebSearchToolResultError

Accepts one of the following:

const WebSearchToolResultErrorWebSearchToolResultError WebSearchToolResultError = "web_search_tool_result_error"

type WebSearchToolResultBlockContentArray []WebSearchResultBlock

EncryptedContent string

PageAge string

Title string

Type WebSearchResult

Accepts one of the following:

const WebSearchResultWebSearchResult WebSearchResult = "web_search_result"

URL string

ToolUseID string

Type WebSearchToolResult

Accepts one of the following:

const WebSearchToolResultWebSearchToolResult WebSearchToolResult = "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:

type Model string

The model that will complete your prompt.

See models for additional details and options.

Accepts one of the following:

const ModelClaudeOpus4_5_20251101 Model = "claude-opus-4-5-20251101"

Premium model combining maximum intelligence with practical performance

const ModelClaudeOpus4_5 Model = "claude-opus-4-5"

Premium model combining maximum intelligence with practical performance

const ModelClaude3_7SonnetLatest Model = "claude-3-7-sonnet-latest"

High-performance model with early extended thinking

const ModelClaude3_7Sonnet20250219 Model = "claude-3-7-sonnet-20250219"

High-performance model with early extended thinking

const ModelClaude3_5HaikuLatest Model = "claude-3-5-haiku-latest"

Fastest and most compact model for near-instant responsiveness

const ModelClaude3_5Haiku20241022 Model = "claude-3-5-haiku-20241022"

Our fastest model

const ModelClaudeHaiku4_5 Model = "claude-haiku-4-5"

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

const ModelClaudeHaiku4_5_20251001 Model = "claude-haiku-4-5-20251001"

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

const ModelClaudeSonnet4_20250514 Model = "claude-sonnet-4-20250514"

High-performance model with extended thinking

const ModelClaudeSonnet4_0 Model = "claude-sonnet-4-0"

High-performance model with extended thinking

const ModelClaude4Sonnet20250514 Model = "claude-4-sonnet-20250514"

High-performance model with extended thinking

const ModelClaudeSonnet4_5 Model = "claude-sonnet-4-5"

Our best model for real-world agents and coding

const ModelClaudeSonnet4_5_20250929 Model = "claude-sonnet-4-5-20250929"

Our best model for real-world agents and coding

const ModelClaudeOpus4_0 Model = "claude-opus-4-0"

Our most capable model

const ModelClaudeOpus4_20250514 Model = "claude-opus-4-20250514"

Our most capable model

const ModelClaude4Opus20250514 Model = "claude-4-opus-20250514"

Our most capable model

const ModelClaudeOpus4_1_20250805 Model = "claude-opus-4-1-20250805"

Our most capable model

const ModelClaude3OpusLatest Model = "claude-3-opus-latest"

Excels at writing and complex tasks

const ModelClaude_3_Opus_20240229 Model = "claude-3-opus-20240229"

Excels at writing and complex tasks

const ModelClaude_3_Haiku_20240307 Model = "claude-3-haiku-20240307"

Our previous most fast and cost-effective

string

Role Assistant

Conversational role of the generated message.

This will always be "assistant".

Accepts one of the following:

const AssistantAssistant Assistant = "assistant"

StopReason 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:

const StopReasonEndTurn StopReason = "end_turn"

const StopReasonMaxTokens StopReason = "max_tokens"

const StopReasonStopSequence StopReason = "stop_sequence"

const StopReasonToolUse StopReason = "tool_use"

const StopReasonPauseTurn StopReason = "pause_turn"

const StopReasonRefusal StopReason = "refusal"

StopSequence 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 Message

Object type.

For Messages, this is always "message".

Accepts one of the following:

const MessageMessage 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 CacheCreation

Breakdown of cached tokens by TTL

Ephemeral1hInputTokens int64

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

minimum0

Ephemeral5mInputTokens int64

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

minimum0

CacheCreationInputTokens int64

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

minimum0

CacheReadInputTokens int64

The number of input tokens read from the cache.

minimum0

InputTokens int64

The number of input tokens which were used.

minimum0

OutputTokens int64

The number of output tokens which were used.

minimum0

ServerToolUse ServerToolUsage

The number of server tool requests.

WebSearchRequests int64

The number of web search tool requests.

minimum0

ServiceTier UsageServiceTier

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

Accepts one of the following:

const UsageServiceTierStandard UsageServiceTier = "standard"

const UsageServiceTierPriority UsageServiceTier = "priority"

const UsageServiceTierBatch UsageServiceTier = "batch"

Type Succeeded

Accepts one of the following:

const SucceededSucceeded Succeeded = "succeeded"

type MessageBatchErroredResult struct{…}

Error ErrorResponse

Error ErrorObjectUnion

Accepts one of the following:

type InvalidRequestError struct{…}

Message string

Type InvalidRequestError

Accepts one of the following:

const InvalidRequestErrorInvalidRequestError InvalidRequestError = "invalid_request_error"

type AuthenticationError struct{…}

Message string

Type AuthenticationError

Accepts one of the following:

const AuthenticationErrorAuthenticationError AuthenticationError = "authentication_error"

type BillingError struct{…}

Message string

Type BillingError

Accepts one of the following:

const BillingErrorBillingError BillingError = "billing_error"

type PermissionError struct{…}

Message string

Type PermissionError

Accepts one of the following:

const PermissionErrorPermissionError PermissionError = "permission_error"

type NotFoundError struct{…}

Message string

Type NotFoundError

Accepts one of the following:

const NotFoundErrorNotFoundError NotFoundError = "not_found_error"

type RateLimitError struct{…}

Message string

Type RateLimitError

Accepts one of the following:

const RateLimitErrorRateLimitError RateLimitError = "rate_limit_error"

type GatewayTimeoutError struct{…}

Message string

Type TimeoutError

Accepts one of the following:

const TimeoutErrorTimeoutError TimeoutError = "timeout_error"

type APIErrorObject struct{…}

Message string

Type APIError

Accepts one of the following:

const APIErrorAPIError APIError = "api_error"

type OverloadedError struct{…}

Message string

Type OverloadedError

Accepts one of the following:

const OverloadedErrorOverloadedError OverloadedError = "overloaded_error"

RequestID string

Type Error

Accepts one of the following:

const ErrorError Error = "error"

Type Errored

Accepts one of the following:

const ErroredErrored Errored = "errored"

type MessageBatchCanceledResult struct{…}

Type Canceled

Accepts one of the following:

const CanceledCanceled Canceled = "canceled"

type MessageBatchExpiredResult struct{…}

Type Expired

Accepts one of the following:

const ExpiredExpired Expired = "expired"

Retrieve Message Batch results

package main

import (
  "context"
  "fmt"

  "github.com/anthropics/anthropic-sdk-go"
  "github.com/anthropics/anthropic-sdk-go/option"
)

func main() {
  client := anthropic.NewClient(
    option.WithAPIKey("my-anthropic-api-key"),
  )
  stream := client.Messages.Batches.ResultsStreaming(context.TODO(), "message_batch_id")
  if stream.Err() != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", messageBatchIndividualResponse.CustomID)
}

Returns Examples

package main import ( "context" "fmt" "github.com/anthropics/anthropic-sdk-go" "github.com/anthropics/anthropic-sdk-go/option" ) func main() { client := anthropic.NewClient( option.WithAPIKey("my-anthropic-api-key"), ) stream := client.Messages.Batches.ResultsStreaming(context.TODO(), "message_batch_id") if stream.Err() != nil { panic(err.Error()) } fmt.Printf("%+v\n", messageBatchIndividualResponse.CustomID) }