View Source OpenAi.Usage (OpenAI REST API Client v1.0.0)

Provides API endpoints related to usage

Summary

Functions

usage_audio_speeches(opts \\ [])

Get audio speeches usage details for the organization.

usage_audio_transcriptions(opts \\ [])

Get audio transcriptions usage details for the organization.

usage_code_interpreter_sessions(opts \\ [])

Get code interpreter sessions usage details for the organization.

usage_completions(opts \\ [])

Get completions usage details for the organization.

usage_costs(opts \\ [])

Get costs details for the organization.

usage_embeddings(opts \\ [])

Get embeddings usage details for the organization.

usage_images(opts \\ [])

Get images usage details for the organization.

usage_moderations(opts \\ [])

Get moderations usage details for the organization.

usage_vector_stores(opts \\ [])

Get vector stores usage details for the organization.

Functions

Link to this function

usage_audio_speeches(opts \\ [])

View Source 
@spec usage_audio_speeches(opts :: keyword()) ::
  {:ok, OpenAi.Usage.Response.t()} | {:error, OpenAi.Error.error()}

Get audio speeches usage details for the organization.

Options

  • start_time: Start time (Unix seconds) of the query time range, inclusive.

  • end_time: End time (Unix seconds) of the query time range, exclusive.

  • bucket_width: Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

  • project_ids: Return only usage for these projects.

  • user_ids: Return only usage for these users.

  • api_key_ids: Return only usage for these API keys.

  • models: Return only usage for these models.

  • group_by: Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model or any combination of them.

  • limit: Specifies the number of buckets to return.

    • bucket_width=1d: default: 7, max: 31
    • bucket_width=1h: default: 24, max: 168
    • bucket_width=1m: default: 60, max: 1440

  • page: A cursor for use in pagination. Corresponding to the next_page field from the previous response.

Link to this function

usage_audio_transcriptions(opts \\ [])

View Source 
@spec usage_audio_transcriptions(opts :: keyword()) ::
  {:ok, OpenAi.Usage.Response.t()} | {:error, OpenAi.Error.error()}

Get audio transcriptions usage details for the organization.

Options

  • start_time: Start time (Unix seconds) of the query time range, inclusive.

  • end_time: End time (Unix seconds) of the query time range, exclusive.

  • bucket_width: Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

  • project_ids: Return only usage for these projects.

  • user_ids: Return only usage for these users.

  • api_key_ids: Return only usage for these API keys.

  • models: Return only usage for these models.

  • group_by: Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model or any combination of them.

  • limit: Specifies the number of buckets to return.

    • bucket_width=1d: default: 7, max: 31
    • bucket_width=1h: default: 24, max: 168
    • bucket_width=1m: default: 60, max: 1440

  • page: A cursor for use in pagination. Corresponding to the next_page field from the previous response.

Link to this function

usage_code_interpreter_sessions(opts \\ [])

View Source 
@spec usage_code_interpreter_sessions(opts :: keyword()) ::
  {:ok, OpenAi.Usage.Response.t()} | {:error, OpenAi.Error.error()}

Get code interpreter sessions usage details for the organization.

Options

  • start_time: Start time (Unix seconds) of the query time range, inclusive.

  • end_time: End time (Unix seconds) of the query time range, exclusive.

  • bucket_width: Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

  • project_ids: Return only usage for these projects.

  • group_by: Group the usage data by the specified fields. Support fields include project_id.

  • limit: Specifies the number of buckets to return.

    • bucket_width=1d: default: 7, max: 31
    • bucket_width=1h: default: 24, max: 168
    • bucket_width=1m: default: 60, max: 1440

  • page: A cursor for use in pagination. Corresponding to the next_page field from the previous response.

Link to this function

usage_completions(opts \\ [])

View Source 
@spec usage_completions(opts :: keyword()) ::
  {:ok, OpenAi.Usage.Response.t()} | {:error, OpenAi.Error.error()}

Get completions usage details for the organization.

Options

  • start_time: Start time (Unix seconds) of the query time range, inclusive.

  • end_time: End time (Unix seconds) of the query time range, exclusive.

  • bucket_width: Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

  • project_ids: Return only usage for these projects.

  • user_ids: Return only usage for these users.

  • api_key_ids: Return only usage for these API keys.

  • models: Return only usage for these models.

  • batch: If true, return batch jobs only. If false, return non-batch jobs only. By default, return both.

  • group_by: Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model, batch or any combination of them.

  • limit: Specifies the number of buckets to return.

    • bucket_width=1d: default: 7, max: 31
    • bucket_width=1h: default: 24, max: 168
    • bucket_width=1m: default: 60, max: 1440

  • page: A cursor for use in pagination. Corresponding to the next_page field from the previous response.

Link to this function

usage_costs(opts \\ [])

View Source 
@spec usage_costs(opts :: keyword()) ::
  {:ok, OpenAi.Usage.Response.t()} | {:error, OpenAi.Error.error()}

Get costs details for the organization.

Options

  • start_time: Start time (Unix seconds) of the query time range, inclusive.

  • end_time: End time (Unix seconds) of the query time range, exclusive.

  • bucket_width: Width of each time bucket in response. Currently only 1d is supported, default to 1d.

  • project_ids: Return only costs for these projects.

  • group_by: Group the costs by the specified fields. Support fields include project_id, line_item and any combination of them.

  • limit: A limit on the number of buckets to be returned. Limit can range between 1 and 180, and the default is 7.

  • page: A cursor for use in pagination. Corresponding to the next_page field from the previous response.

Link to this function

usage_embeddings(opts \\ [])

View Source 
@spec usage_embeddings(opts :: keyword()) ::
  {:ok, OpenAi.Usage.Response.t()} | {:error, OpenAi.Error.error()}

Get embeddings usage details for the organization.

Options

  • start_time: Start time (Unix seconds) of the query time range, inclusive.

  • end_time: End time (Unix seconds) of the query time range, exclusive.

  • bucket_width: Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

  • project_ids: Return only usage for these projects.

  • user_ids: Return only usage for these users.

  • api_key_ids: Return only usage for these API keys.

  • models: Return only usage for these models.

  • group_by: Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model or any combination of them.

  • limit: Specifies the number of buckets to return.

    • bucket_width=1d: default: 7, max: 31
    • bucket_width=1h: default: 24, max: 168
    • bucket_width=1m: default: 60, max: 1440

  • page: A cursor for use in pagination. Corresponding to the next_page field from the previous response.

Link to this function

usage_images(opts \\ [])

View Source 
@spec usage_images(opts :: keyword()) ::
  {:ok, OpenAi.Usage.Response.t()} | {:error, OpenAi.Error.error()}

Get images usage details for the organization.

Options

  • start_time: Start time (Unix seconds) of the query time range, inclusive.

  • end_time: End time (Unix seconds) of the query time range, exclusive.

  • bucket_width: Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

  • sources: Return only usages for these sources. Possible values are image.generation, image.edit, image.variation or any combination of them.

  • sizes: Return only usages for these image sizes. Possible values are 256x256, 512x512, 1024x1024, 1792x1792, 1024x1792 or any combination of them.

  • project_ids: Return only usage for these projects.

  • user_ids: Return only usage for these users.

  • api_key_ids: Return only usage for these API keys.

  • models: Return only usage for these models.

  • group_by: Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model, size, source or any combination of them.

  • limit: Specifies the number of buckets to return.

    • bucket_width=1d: default: 7, max: 31
    • bucket_width=1h: default: 24, max: 168
    • bucket_width=1m: default: 60, max: 1440

  • page: A cursor for use in pagination. Corresponding to the next_page field from the previous response.

Link to this function

usage_moderations(opts \\ [])

View Source 
@spec usage_moderations(opts :: keyword()) ::
  {:ok, OpenAi.Usage.Response.t()} | {:error, OpenAi.Error.error()}

Get moderations usage details for the organization.

Options

  • start_time: Start time (Unix seconds) of the query time range, inclusive.

  • end_time: End time (Unix seconds) of the query time range, exclusive.

  • bucket_width: Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

  • project_ids: Return only usage for these projects.

  • user_ids: Return only usage for these users.

  • api_key_ids: Return only usage for these API keys.

  • models: Return only usage for these models.

  • group_by: Group the usage data by the specified fields. Support fields include project_id, user_id, api_key_id, model or any combination of them.

  • limit: Specifies the number of buckets to return.

    • bucket_width=1d: default: 7, max: 31
    • bucket_width=1h: default: 24, max: 168
    • bucket_width=1m: default: 60, max: 1440

  • page: A cursor for use in pagination. Corresponding to the next_page field from the previous response.

Link to this function

usage_vector_stores(opts \\ [])

View Source 
@spec usage_vector_stores(opts :: keyword()) ::
  {:ok, OpenAi.Usage.Response.t()} | {:error, OpenAi.Error.error()}

Get vector stores usage details for the organization.

Options

  • start_time: Start time (Unix seconds) of the query time range, inclusive.

  • end_time: End time (Unix seconds) of the query time range, exclusive.

  • bucket_width: Width of each time bucket in response. Currently 1m, 1h and 1d are supported, default to 1d.

  • project_ids: Return only usage for these projects.

  • group_by: Group the usage data by the specified fields. Support fields include project_id.

  • limit: Specifies the number of buckets to return.

    • bucket_width=1d: default: 7, max: 31
    • bucket_width=1h: default: 24, max: 168
    • bucket_width=1m: default: 60, max: 1440

  • page: A cursor for use in pagination. Corresponding to the next_page field from the previous response.