haive.core.models.metadata
==========================

.. py:module:: haive.core.models.metadata

.. autoapi-nested-parse::

   Model metadata utilities for LLM configurations.

   This module provides utilities for downloading, caching, and accessing
   model metadata from LiteLLM's model_prices_and_context_window.json.



Classes
-------

.. autoapisummary::

   haive.core.models.metadata.ModelMetadata


Functions
---------

.. autoapisummary::

   haive.core.models.metadata.get_model_metadata


Module Contents
---------------

.. py:class:: ModelMetadata

   A class to store and provide model metadata.

   This class encapsulates metadata about a language model, including
   its pricing, context window limits, and provider information.


   .. py:property:: context_window
      :type: int


      Get the context window size for this model.


   .. py:property:: pricing
      :type: dict[str, float]


      Get the pricing information for this model.


.. py:function:: get_model_metadata(model_name, provider = None, force_refresh = False)

   Get metadata for a specific model with improved matching.

   This function tries to find the most relevant model metadata based on the
   model name and provider, with multiple fallback strategies.

   :param model_name: Name of the model (e.g., "gpt-4", "claude-3-opus")
   :param provider: Optional provider prefix (e.g., "azure", "anthropic")
   :param force_refresh: Force download fresh metadata

   :returns: Model metadata dictionary or empty dict if not found