scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-16 23:41:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

docs(fireworks-ai): describe the cache-read fallback without asserting provider billing

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
kerry 2026-09-16 01:44:30 +00:00
parent 8352045f32
commit 91c7f75864
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
litellm/llms/fireworks_ai/cost_calculator.py
View file

@ -68,8 +68,8 @@ def _resolve_model_info(model: str) -> ModelInfo:
def _with_cache_read_fallback(model_info: ModelInfo) -> ModelInfo:
"""Most fireworks_ai price-map entries publish no cache-read rate though the provider bills
cached reads at the input rate; the shared map is never mutated, so a copy carries the fallback."""
"""Entries without a cache-read rate keep the previous calculator's input-rate fallback for cached
reads (LIT-7845 tracks the documented discount); the shared map is never mutated, so a copy carries it."""
input_rate: Final = model_info.get("input_cost_per_token")
if model_info.get("cache_read_input_token_cost") is not None or input_rate is None:
return model_info