Comparing
litellm_fix_check_responses_cost_tests
(48a6823
) withmain
(2bb7387
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-2%
83.7 µs85.3 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py-1%
186.9 µs189.5 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py+1%
86.6 µs85.7 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py-1%
1.7 ms1.7 ms
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py-1%
84.8 µs85.4 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py-1%
87.2 µs87.7 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
239.8 µs238.7 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
543.8 µs541.6 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
149.2 µs148.9 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
142.6 µs143 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
87.5 µs87.7 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
569.2 µs568.5 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
541.9 µs542.4 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
141.8 µs141.7 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
146.3 µs146.3 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
418.1 µs418 µs
Commits
Click on a commit to change the comparison rangeBase
main
2bb7387
-0.23%
fix(test): update check_responses_cost tests for _expire_stale_rows
48a6823
5 months ago
by yuneng-berri