Comparing
qiniu:fix/router-register-model-cost-responses-stripped
(73eefc8
) withshin_agent_oss_staging_05_09_2026
(fa81017
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py+1%
137.9 µs136.8 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+1%
79.7 µs79 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py-1%
79.8 µs80.4 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+1%
82.8 µs82.2 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py+1%
544.1 µs540.5 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
542.7 µs540.7 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
564.7 µs566.6 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
235.2 µs235.9 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.1 µs81.9 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
184.1 µs183.7 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
414.5 µs413.7 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
142 µs141.7 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.2 µs138 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
143.6 µs143.7 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.7 µs79.7 µs
Commits
Click on a commit to change the comparison rangeBase
main
fa81017
+0.18%
fix(router): register model info under responses/-stripped variant
73eefc8
4 months ago
by S0ngRu1