Comparing
litellm_fix-websearch-interception-logging
(bec448d
) withlitellm_ishaan_april10
(d0e347a
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+2%
85.8 µs83.9 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
240.3 µs239.4 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
572.7 µs572.6 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
418 µs418 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
187.1 µs187.3 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
141.8 µs142 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85 µs85.2 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
148.8 µs149.1 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
89 µs89.3 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
142.6 µs143.1 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
146.8 µs147.3 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.3 µs87.8 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py-1%
85.2 µs85.6 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py-1%
543.2 µs546.3 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py-1%
541.8 µs546.3 µs
Commits
Click on a commit to change the comparison rangeBase
main
d0e347a
-0.13%
fix(websearch_interception): ensure spend/cost logging runs when stream=True
cb057ad
8 days ago
by Sameerlite+0.05%
Merge pull request #25524 from BerriAI/main
bec448d
7 days ago
by Sameerlite