The user must already be a member of the organization (see
    openai_invite_user / openai_list_users) — this call cannot invite
    someone new to the org.

    Args:
        project_id: The project's ID (see openai_list_projects).
        user_id: The organization member's user ID (see openai_list_users).
        role: Project role to grant — `owner` or `member`.
    

    Args:
        project_id: The project's ID (see openai_list_projects).
    

    Args:
        name: The project's friendly name (appears in usage/cost reports).
    

    By default this also creates a `member`-role project membership and an
    API key for the account. IMPORTANT: the response contains the API key's
    PLAINTEXT value — this is the only time it is ever shown. Surface it to
    the user immediately so they can store it; it cannot be retrieved again.

    Args:
        project_id: The project's ID (see openai_list_projects).
        name: Name for the new service account.
        create_service_account_only: If True, skip creating the default role/API key.
    

    Args:
        invite_id: The invite's ID (see openai_list_invites).
    

    Fails if the key belongs to a service account — delete the service
    account instead (openai_delete_service_account) to revoke that key.

    Args:
        project_id: The project's ID (see openai_list_projects).
        api_key_id: The API key's ID (see openai_list_project_api_keys).
    

    Args:
        project_id: The project's ID (see openai_list_projects).
        service_account_id: The service account's ID (see openai_list_service_accounts).
    

    Args:
        start_time: Start of the query range, inclusive (Unix seconds).
        end_time: End of the query range, exclusive (Unix seconds).
        bucket_width: Time bucket size — only `1d` is currently supported.
        group_by: Fields to group by — project_id, line_item, api_key_id.
        project_ids: Only include costs for these projects.
        api_key_ids: Only include costs for these API keys.
        limit: Number of buckets to return (1-180, default 7).
        page: Pagination cursor from a previous response's `next_page`.
    

    Args:
        invite_id: The invite's ID (see openai_list_invites).
    

    Args:
        project_id: The project's ID (see openai_list_projects).
    

    Args:
        project_id: The project's ID (see openai_list_projects).
        api_key_id: The API key's ID (see openai_list_project_api_keys).
    

    Args:
        project_id: The project's ID (see openai_list_projects).
        user_id: The member's user ID (see openai_list_project_users).
    

    Args:
        project_id: The project's ID (see openai_list_projects).
        service_account_id: The service account's ID (see openai_list_service_accounts).
    

    `limit` caps the number of time buckets returned, with different
    defaults/maximums per bucket_width: 1d -> default 7, max 31; 1h ->
    default 24, max 168; 1m -> default 60, max 1440.

    Args:
        category: Which usage type to query — one of: completions,
            embeddings, moderations, images, audio_speeches,
            audio_transcriptions, vector_stores, code_interpreter_sessions,
            file_search_calls, web_search_calls.
        start_time: Start of the query range, inclusive (Unix seconds).
        end_time: End of the query range, exclusive (Unix seconds).
        bucket_width: Time bucket size — `1m`, `1h`, or `1d` (default `1d`).
        group_by: Fields to group by, e.g. project_id, user_id, api_key_id,
            model, batch, service_tier (supported fields vary by category).
        project_ids: Only include usage for these projects.
        user_ids: Only include usage for these users.
        api_key_ids: Only include usage for these API keys.
        models: Only include usage for these models.
        limit: Number of time buckets to return.
        page: Pagination cursor from a previous response's `next_page`.
    

    Args:
        user_id: The member's user ID (see openai_list_users).
    

    The invite must be accepted by the user before they gain access. Its
    "status" starts at `pending` until accepted.

    Args:
        email: Email address to invite.
        role: Organization role to grant — `owner` or `reader`.
        projects: Optional list of `{"id": <project_id>, "role": "owner"|"member"}`
            to grant project membership at the same time the invite is accepted.
            If omitted, the user is invited to the default project (legacy
            behavior). Pass an empty list to invite them to no projects at all.
    

    Args:
        effective_start_time: Only events at/after this Unix timestamp (seconds).
        effective_end_time: Only events before this Unix timestamp (seconds).
        actor_emails: Only events performed by users with these emails.
        actor_ids: Only events performed by these actors (user, service
            account, or API key tracking IDs).
        event_types: Only events of these types, e.g. `project.created`,
            `user.added`, `api_key.deleted`, `invite.sent`. See
            https://platform.openai.com/docs/api-reference/audit-logs/object
            for the full enum.
        project_ids: Only events scoped to these projects.
        resource_ids: Only events affecting these resource IDs.
        after: Pagination cursor from a previous response's `last_id`.
        before: Pagination cursor to fetch the previous page.
        limit: Maximum number of events to return per page.
    

    Each invite's "status" is one of `pending`, `accepted`, or `expired`.

    Args:
        after: Pagination cursor from a previous response's `last_id`.
        limit: Maximum number of invites to return per page.
    

    Args:
        project_id: The project's ID (see openai_list_projects).
        owner_project_access: Filter by whether the key owner currently has
            project access — `active`, `inactive`, or `any`.
        after: Pagination cursor from a previous response's `last_id`.
        limit: Maximum number of keys to return per page.
    

    Args:
        include_archived: If True, also return archived projects (excluded by default).
        after: Pagination cursor from a previous response's `last_id`.
        limit: Maximum number of projects to return per page.
    

    Args:
        project_id: The project's ID (see openai_list_projects).
        after: Pagination cursor from a previous response's `last_id`.
        limit: Maximum number of users to return per page.
    

    Args:
        project_id: The project's ID (see openai_list_projects).
        after: Pagination cursor from a previous response's `last_id`.
        before: Pagination cursor to fetch the previous page.
        limit: Maximum number of rate limit entries to return per page.
    

    Args:
        project_id: The project's ID (see openai_list_projects).
        after: Pagination cursor from a previous response's `last_id`.
        limit: Maximum number of service accounts to return per page.
    

    Args:
        emails: Filter by these email addresses.
        after: Pagination cursor from a previous response's `last_id`.
        limit: Maximum number of users to return per page.
    

    Args:
        project_id: The project's ID (see openai_list_projects).
        user_id: The member's user ID (see openai_list_project_users).
    

    Args:
        user_id: The member's user ID (see openai_list_users).
    

    Args:
        project_id: The project's ID (see openai_list_projects).
        name: The new project name.
    

    Args:
        project_id: The project's ID (see openai_list_projects).
        user_id: The member's user ID (see openai_list_project_users).
        role: New project role — `owner` or `member`.
    

    Each `max_*` field only applies to relevant model types (e.g.
    max_images_per_1_minute only matters for image models) — check
    openai_list_rate_limits first to see which fields are present for the
    target model before changing them.

    Args:
        project_id: The project's ID (see openai_list_projects).
        rate_limit_id: The rate limit entry's ID (see openai_list_rate_limits).
        max_requests_per_1_minute: New requests-per-minute limit.
        max_tokens_per_1_minute: New tokens-per-minute limit.
        max_images_per_1_minute: New images-per-minute limit.
        max_audio_megabytes_per_1_minute: New audio-megabytes-per-minute limit.
        max_requests_per_1_day: New requests-per-day limit.
        batch_1_day_max_input_tokens: New batch max input tokens per day.
    

    Args:
        project_id: The project's ID (see openai_list_projects).
        service_account_id: The service account's ID (see openai_list_service_accounts).
        name: New name for the service account.
        role: New project role — `owner` or `member`.
    

    Args:
        user_id: The member's user ID (see openai_list_users).
        role: New organization role — `owner` or `reader`.