Comparing
litellm_internal_staging
(eebb80f
) withlitellm_gemini_provider_default_thinking
(26fcbc9
)0%
- Untouched
- 16
This run is associated to a commit that was force-pushed
It will not be associated with its branch history. Be careful when comparing its performance to other runs.Benchmarks
16 total
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+3%
82.4 µs80 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+3%
81.2 µs78.9 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py+1%
80.8 µs80.1 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
413.6 µs411.6 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
236.6 µs235.6 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
143.9 µs144.1 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
140.9 µs141.2 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
182.7 µs183.4 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.4 µs79.7 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
137.5 µs138 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
539.9 µs542.6 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py-1%
81.7 µs82.1 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py-1%
538.3 µs542.7 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-1%
136.5 µs137.8 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py-1%
1.7 ms1.7 ms
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py-2%
561.3 µs573.2 µs
Commits
Click on a commit to change the comparison rangeBase
main
26fcbc9
+0.01%
Merge pull request #26208 from BerriAI/litellm_individual-team-member-budgets
eebb80f
13 hours ago
by yuneng-berri