Avatar for the BerriAI user
BerriAI
litellm
BlogDocsChangelog

Performance History

Latest Results

docs: add SWE-bench performance results to compress() docs Include benchmark table from Opus eval (5 problems, trigger=10k) showing 72% cost savings with file-level quality fully preserved. Add metric explanations and eval runner examples. Co-Authored-By: Claude Opus 4.6 <[email protected]>
claude/zealous-black
8 minutes ago
fix(router): honor RetryPolicy.InternalServerErrorRetries in dispatcher
michelligabriele:fix/retry-policy-internal-server-error
8 minutes ago
refactor: module level imports for ensure_litellm_metadata and CodeQL
GraySwanAI:fix/send-litellm-metadata-guardrail-precall
46 minutes ago
refactor: remove unused BaseTranslation._ensure_litellm_metadata
GraySwanAI:fix/send-litellm-metadata-guardrail-precall
47 minutes ago
fix: ensure `litellm_metadata` is attached to pre_call to align with post_call
GraySwanAI:fix/send-litellm-metadata-guardrail-precall
56 minutes ago

Latest Branches

CodSpeed Performance Gauge
0%
feat: add litellm.compress() — BM25-based prompt compression with retrieval tool#25637
12 minutes ago
b0e4d9c
claude/zealous-black
CodSpeed Performance Gauge
0%
13 minutes ago
597cd00
michelligabriele:fix/retry-policy-internal-server-error
CodSpeed Performance Gauge
-1%
37 minutes ago
e398b52
litellm_ishaan_april13
© 2026 CodSpeed Technology
Home Terms Privacy Docs