Comparing
litellm_hotfix_gpt-5.5-azure
(0edb687
) withmain
(d21e90f
)0%
- Untouched
- 16
Benchmarks
16 total
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py+1%
236.6 µs235.2 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py+1%
138.6 µs137.8 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py+1%
413.4 µs411.1 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py+1%
141.8 µs141 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
543.8 µs541.4 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
183.6 µs182.9 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
542 µs540.4 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
564.4 µs563 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py0%
79 µs78.9 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.5 µs79.7 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
79.8 µs80 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
81.8 µs82.1 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py-1%
144.1 µs145.2 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-1%
137 µs138.2 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-1%
80 µs80.8 µs
Commits
Click on a commit to change the comparison rangeBase
main
d21e90f
-0.4%
feat(azure): add azure/gpt-5.5 + azure/gpt-5.5-pro entries (+ dated variants)
6d320bc
3 hours ago
by mateo-berri+0.44%
test: register supports_low_reasoning_effort in cost-map JSON schema
0edb687
2 hours ago
by mateo-berri