Comparing
litellm_dev_04_02_2026_p1
(9db062c
) withlitellm_oss_staging_04_02_2026_p1
(1e5b79d
)0%
- Untouched
- 16
Benchmarks
16 total
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py+2%
1.7 ms1.7 ms
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py-1%
85.6 µs86.5 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+1%
85.4 µs84.6 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py-1%
146.4 µs147.2 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
187.4 µs187.9 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
415.5 µs414.6 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.3 µs85.5 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
542.2 µs543 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.5 µs87.6 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
141.8 µs141.6 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
241.5 µs241.4 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
148.8 µs148.9 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
88.8 µs88.8 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
571.4 µs571.5 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
542.4 µs542.5 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
143 µs143 µs
Commits
Click on a commit to change the comparison rangeBase
main
1e5b79d
+0.05%
fix: Anthropic web search cost not tracked for Chat Completions
9db062c
5 months ago
by krrish-berri-2