Comparing
StatPan:fix/gemini-full-api-base-duplicate-path
(f981e4a
) withlitellm_oss_staging
(934ecdc
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.2 µs137.8 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%
566.7 µs565.8 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
143.8 µs143.7 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
136.7 µs136.6 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.8 µs79.7 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.2 µs82.1 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
183.5 µs183.4 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
413.4 µs413.6 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
234.6 µs234.7 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
541 µs542.7 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
141.8 µs142.4 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py-1%
540.8 µs543.9 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py-1%
81 µs82.1 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-2%
80.9 µs82.7 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-2%
78.8 µs80.6 µs
Commits
Click on a commit to change the comparison rangeBase
main
934ecdc
-0.58%
test(gemini): cover full-route custom api_base handling
0d6d94c
23 days ago
by StatPan+0.19%
test(vertex): restore credential project validation expectation
f981e4a
23 days ago
by StatPan