Request headers for troubleshooting in Yandex AI Studio

If something went wrong while sending API requests and you need help, contact technical support.

The support team will solve your issue faster if you use advanced HTTP request and response headers.

Request headersRequest headers

When sending HTTP requests, use the following headers:

• x-client-request-id is a unique request ID. We recommend using a UUID. Send this ID to the technical support team to help us find a specific request in the system and assist you.

  You can generate a UUID either online or through the library for the programming language you use.

• x-data-logging-enabled: Flag that allows saving the data provided by the user in the request.

  By default, all requests to AI Studio are logged. Logging will help resolve your issue if you also specify the request ID when contacting support. You can disable logging if you need to include sensitive information in your request.

ExamplesExamples

You can use the headers below to locate your asynchronous query to a model:

export FOLDER_ID=<folder_ID>
export IAM_TOKEN=<IAM_token>
curl \
  --request POST \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer ${IAM_TOKEN}" \
  --header "x-folder-id: ${FOLDER_ID}" \
  --data "@<path_to_JSON_file>" \
  "https://llm.api.cloud.yandex.net/foundationModels/v1/completionAsync"

Response headersResponse headers

Each server response contains headers that provide even more information about the request execution:

• x-request-id: Unique response ID
• x-server-trace-id: Unique request execution log ID

To get the x-request-id and x-server-trace-id values, your application must log server response headers.

You can find an example of implementing access to gRPC headers in the grpc-go documentation.