Получение результатов пакета сообщений

GET

messages

batches

{message_batch_id}

results

curl https://api.anthropic.com/v1/messages/batches/msgbatch_01HkcTjaV5uDC8jWR4ZsDV8d/results \
     --header "x-api-key: $ANTHROPIC_API_KEY" \
     --header "anthropic-version: 2023-06-01"

{"custom_id":"my-second-request","result":{"type":"succeeded","message":{"id":"msg_014VwiXbi91y3JMjcpyGBHX5","type":"message","role":"assistant","model":"claude-3-5-sonnet-20240620","content":[{"type":"text","text":"Здравствуйте снова! Рад вас видеть. Чем могу помочь сегодня? Есть ли что-то конкретное, о чем вы хотели бы поговорить, или у вас есть какие-то вопросы?"}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":11,"output_tokens":36}}}}
{"custom_id":"my-first-request","result":{"type":"succeeded","message":{"id":"msg_01FqfsLoHwgeFbguDgpz48m7","type":"message","role":"assistant","model":"claude-3-5-sonnet-20240620","content":[{"type":"text","text":"Здравствуйте! Чем могу помочь вам сегодня? Не стесняйтесь задавать любые вопросы или дайте мне знать, если есть что-то, о чем вы хотели бы поговорить."}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":10,"output_tokens":34}}}}

Путь для получения результатов пакета сообщений должен быть взят из results_url пакета. Этот путь не следует предполагать заранее, так как он может измениться.

{"custom_id":"my-second-request","result":{"type":"succeeded","message":{"id":"msg_014VwiXbi91y3JMjcpyGBHX5","type":"message","role":"assistant","model":"claude-3-5-sonnet-20240620","content":[{"type":"text","text":"Здравствуйте снова! Рад вас видеть. Чем могу помочь сегодня? Есть ли что-то конкретное, о чем вы хотели бы поговорить, или у вас есть какие-то вопросы?"}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":11,"output_tokens":36}}}}
{"custom_id":"my-first-request","result":{"type":"succeeded","message":{"id":"msg_01FqfsLoHwgeFbguDgpz48m7","type":"message","role":"assistant","model":"claude-3-5-sonnet-20240620","content":[{"type":"text","text":"Здравствуйте! Чем могу помочь вам сегодня? Не стесняйтесь задавать любые вопросы или дайте мне знать, если есть что-то, о чем вы хотели бы поговорить."}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":10,"output_tokens":34}}}}

Headers

anthropic-beta

string[]

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.

anthropic-version

string

required

The version of the Anthropic API you want to use.

Read more about versioning and our version history here.

x-api-key

string

required

Your unique API key for authentication.

This key is required in the header of all API requests, to authenticate your account and access Anthropic's services. Get your API key through the Console. Each key is scoped to a Workspace.

Path Parameters

message_batch_id

string

required

ID of the Message Batch.

Response

200

application/x-jsonl

Successful Response

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

custom_id

string

required

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"

result

object

required

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.

result.message

object

required

result.message.id

string

required

Unique object identifier.

The format and length of IDs may change over time.

Examples:

"msg_013Zva2CMHLNnXjNJJKqJ2EF"

result.message.type

enum<string>

default:message

required

Object type.

For Messages, this is always "message".

Available options:

message

result.message.role

enum<string>

default:assistant

required

Conversational role of the generated message.

This will always be "assistant".

Available options:

assistant

result.message.content

object[]

required

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)"}]

Examples:

[
  {
    "text": "Hi! My name is Claude.",
    "type": "text"
  }
]

result.message.model

string

required

The model that handled the request.

Required string length: 1 - 256

Examples:

"claude-3-7-sonnet-20250219"

result.message.stop_reason

enum<string> | null

required

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.

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.

Available options:

end_turn,

max_tokens,

stop_sequence,

tool_use,

pause_turn,

refusal

result.message.stop_sequence

string | null

required

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.

result.message.usage

object

required

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.

result.message.container

object | null

required

Information about the container used in this request.

This will be non-null if a container tool (e.g. code execution) was used.

Examples:

{
  "content": [
    {
      "text": "Hi! My name is Claude.",
      "type": "text"
    }
  ],
  "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF",
  "model": "claude-3-7-sonnet-20250219",
  "role": "assistant",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "type": "message",
  "usage": {
    "input_tokens": 2095,
    "output_tokens": 503
  }
}

result.type

enum<string>

default:succeeded

required

Available options:

succeeded

Получить пакет сообщений Список пакетов сообщений

curl https://api.anthropic.com/v1/messages/batches/msgbatch_01HkcTjaV5uDC8jWR4ZsDV8d/results \
     --header "x-api-key: $ANTHROPIC_API_KEY" \
     --header "anthropic-version: 2023-06-01"

{"custom_id":"my-second-request","result":{"type":"succeeded","message":{"id":"msg_014VwiXbi91y3JMjcpyGBHX5","type":"message","role":"assistant","model":"claude-3-5-sonnet-20240620","content":[{"type":"text","text":"Здравствуйте снова! Рад вас видеть. Чем могу помочь сегодня? Есть ли что-то конкретное, о чем вы хотели бы поговорить, или у вас есть какие-то вопросы?"}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":11,"output_tokens":36}}}}
{"custom_id":"my-first-request","result":{"type":"succeeded","message":{"id":"msg_01FqfsLoHwgeFbguDgpz48m7","type":"message","role":"assistant","model":"claude-3-5-sonnet-20240620","content":[{"type":"text","text":"Здравствуйте! Чем могу помочь вам сегодня? Не стесняйтесь задавать любые вопросы или дайте мне знать, если есть что-то, о чем вы хотели бы поговорить."}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":10,"output_tokens":34}}}}

SDKs

Использование API

Примеры

Сторонние API

Поддержка и настройка

Справочник API

Получение результатов пакета сообщений

Headers

Path Parameters

Response