chore: add clear_cache helper

README.md

@@ -76,13 +76,15 @@ asyncio.run(main())
 You can customize the cache timeout:
 
 ```python
-from tokonomics import get_model_costs
+from tokonomics import get_model_costs, clear_cache
 
 # Get model costs with custom cache duration (e.g., 1 hour)
 costs = await get_model_costs("gpt-4", cache_timeout=3600)
 if costs:
     print(f"Input cost per token: ${costs['input_cost_per_token']}")
     print(f"Output cost per token: ${costs['output_cost_per_token']}")
+
+clear_cache()
 ```
 
 ### Getting Model Token Limits

src/tokonomics/__init__.py

@@ -1,9 +1,15 @@
 __version__ = "0.2.2"
 
+from tokonomics.core import (
+    get_model_costs,
+    calculate_token_cost,
+    get_model_limits,
+    reset_cache,
+)
 from tokonomics.toko_types import ModelCosts, TokenCosts, TokenLimits
-from tokonomics.core import get_model_costs, calculate_token_cost, get_model_limits
 from tokonomics.pydanticai_cost import calculate_pydantic_cost, Usage
 
+
 __all__ = [
     "ModelCosts",
     "TokenCosts",
@@ -13,4 +19,5 @@
     "calculate_token_cost",
     "get_model_costs",
     "get_model_limits",
+    "reset_cache",
 ]

src/tokonomics/core.py

@@ -27,6 +27,11 @@
 LITELLM_PRICES_URL = "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json"
 
 
+def reset_cache() -> None:
+    """Clear all cached pricing and limit data."""
+    _cost_cache.clear()
+
+
 def _is_numeric(value: str | int | float) -> bool:  # noqa: PYI041
     """Check if a value can be converted to a number."""
     if isinstance(value, int | float):