Comparing
silencedoctor:fix/anthropic-messages-router-cooldown-model-info
(c59024e
) withlitellm_oss_staging
(5be0797
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-3%
80 µs82.8 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py+1%
1.7 ms1.7 ms
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py+1%
416.2 µs411.9 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-1%
79.1 µs79.7 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
184.2 µs183.3 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
562.5 µs560.4 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
142.1 µs142.6 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
560.1 µs561.8 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
564.8 µs565.8 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
234.6 µs235 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.4 µs138.2 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
137 µs136.8 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
80.1 µs80 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.2 µs82.2 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
143.8 µs143.9 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.9 µs79.9 µs
Commits
Click on a commit to change the comparison rangeBase
main
5be0797
-0.09%
fix(llm_http_handler): forward kwargs['model_info'] to litellm_params for /v1/messages
c59024e
3 months ago
by silencedoctor