mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-06 02:48:13 +00:00
Batch retrieval already computed cost/usage on completion, but silently dropped reasoning tokens and never counted per-line success/failure. Adds BatchCostUsageResult (replacing bare cost/usage/models tuples) with successful_requests/failed_requests, and threads reasoning_tokens through the aggregated Usage. Both surface on SpendLogs the same way batch_models already does. |
||
|---|---|---|
| .. | ||
| batch_job_results_furniture.jsonl | ||
| bedrock_batch_completions.jsonl | ||
| conftest.py | ||
| openai_batch_completions.jsonl | ||
| pathrise-convert-1606954137718.json | ||
| test_batch_custom_pricing.py | ||
| test_batch_rate_limits.py | ||
| test_batches_logging_unit_tests.py | ||
| test_bedrock_files_and_batches.py | ||
| test_fine_tuning_api.py | ||
| test_manus_files_all_methods.py | ||
| test_openai_batches_and_files.py | ||
| vertex_batch_completions.jsonl | ||