diff --git a/litellm/llms/openai/responses/count_tokens/token_counter.py b/litellm/llms/openai/responses/count_tokens/token_counter.py index 71f55dcecfd..9849b06cc6e 100644 --- a/litellm/llms/openai/responses/count_tokens/token_counter.py +++ b/litellm/llms/openai/responses/count_tokens/token_counter.py @@ -14,6 +14,10 @@ from typing_extensions import assert_never from litellm._logging import verbose_logger from litellm.litellm_core_utils.asyncify import asyncify from litellm.litellm_core_utils.core_helpers import as_str_mapping +from litellm.litellm_core_utils.reasoning_effort_capability import ( + deployment_reasoning_effort_levels, + resolve_deployment_reasoning_effort, +) from litellm.litellm_core_utils.tool_fields import DropPolicy from litellm.llms.anthropic.messages.context_management import AnthropicContextManagementError from litellm.llms.anthropic.messages.convertible_blocks import deployment_drops_params, unconvertible_blocks_error @@ -37,10 +41,6 @@ from litellm.llms.openai.workload_identity import ( openai_static_api_key, resolve_openai_workload_identity_config, ) -from litellm.router_utils.reasoning_effort_capability import ( - deployment_reasoning_effort_levels, - resolve_deployment_reasoning_effort, -) from litellm.types.utils import CountContextManagement, LlmProviders, TokenCountMessagesFormat, TokenCountResponse # Global handler instance - reuse across all token counting requests