litellm/litellm/batches
kerry e50fc8ba75 fix(batches): bill Bedrock Titan embedding batch lines from inputTextTokenCount
Titan embedding batch output carries the token count as a top-level inputTextTokenCount with no usage block, so the Bedrock batch cost parser recorded 0 tokens and 0 spend for every Titan embedding batch. Parse that field for embedding lines only and leave Converse and Anthropic shaped lines on their existing paths

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-18 05:25:52 +00:00
..
batch_utils.py fix(batches): bill Bedrock Titan embedding batch lines from inputTextTokenCount 2026-09-18 05:25:52 +00:00
main.py fix(vertex_ai): address batch review findings 2026-09-03 19:49:37 -04:00