Comparing
litellm_hotfix_gpt-5.5-support
(d2d676c
) withmain
(7b47dff
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+1%
80.6 µs79.9 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.7 µs138.1 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
136.9 µs136.6 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
235.6 µs235.3 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
568.8 µs568.5 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py0%
78.8 µs78.8 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
144 µs144.1 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.5 µs79.6 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82 µs82.1 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
540.7 µs541.4 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
542.6 µs543.6 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
79.8 µs80 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
413.6 µs414.8 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
141 µs141.4 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py-1%
182.8 µs184.2 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py-1%
1.7 ms1.7 ms
Commits
Click on a commit to change the comparison rangeBase
main
7b47dff
-0.05%
feat(openai): day-0 support for GPT-5.5 and GPT-5.5 Pro
6929ae1
3 hours ago
by mateo-berri-0.05%
fix(openai): mirror reasoning_effort flags onto gpt-5.5 dated variants
d2d676c
3 hours ago
by mateo-berri