Comparing
milan-berri:fix/anthropic-litellm-overhead-time-ms
(9e2de44
) withlitellm_oss_staging_04_02_2026_p1
(488b93c
)+1%
- Untouched
- 16
Benchmarks
16 total
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py+3%
89.5 µs87.3 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py+3%
87.2 µs85.1 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py+2%
87.1 µs85.4 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+2%
88.5 µs86.8 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+2%
85.2 µs83.8 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py+1%
143.1 µs141.7 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
546.4 µs544.4 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
545.5 µs544.1 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
149.3 µs149.1 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
143.4 µs143.3 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
146.7 µs146.6 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
419.5 µs419.3 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
570 µs570.6 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
239.3 µs239.7 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py-1%
186.7 µs188.5 µs
Commits
Click on a commit to change the comparison rangeBase
main
488b93c
+0.74%
fix(anthropic): pass logging_obj to client.post for litellm_overhead_time_ms
9e2de44
1 month ago
by milan-berri