mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-01 07:03:02 +00:00
* fix(cost): preserve zero cache-write prices in batch fallback * fix(cost): retain batch cache charges when ordinary input is free * fix(cost): preserve zero speech and Perplexity search rates * fix(cost): reject unset speech prices before zero defaults * test(cost): consolidate zero-price regression coverage |
||
|---|---|---|
| .. | ||
| docker-entrypoint.d | ||
| litellm-dashboard | ||
| Dockerfile | ||
| nginx.conf | ||