Comparing
Vedanshu7:fix/failure-hook-zero-duration-spend-logs
(33538a2
) withmain
(e4442a4
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.7 µs87.4 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
187.6 µs187.1 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
144.9 µs144.6 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
88.8 µs88.6 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.3 µs85.3 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
418.2 µs417.9 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
85.7 µs85.6 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
547 µs546.8 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
150.4 µs150.6 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
143.3 µs143.4 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
238.5 µs238.9 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
148.3 µs148.6 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
547 µs549.7 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-1%
85.2 µs85.7 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py-1%
568.5 µs571.8 µs
Commits
Click on a commit to change the comparison rangeBase
main
e4442a4
-0.07%
fix(proxy): use actual request start_time for failed spend logs
33538a2
3 hours ago
by Vedanshu7