Comparing
litellm_hotfix_gpt-5.5-minimal-flag
(c333838
) withlitellm_internal_staging
(d21e90f
)0%
- Untouched
- 16
Benchmarks
16 total
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py+1%
236.6 µs235.1 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py+1%
413.4 µs411 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
81.8 µs82.1 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
183.6 µs183 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.6 µs138.3 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.5 µs79.7 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py0%
79 µs78.9 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
137 µs136.9 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
79.8 µs79.9 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
543.8 µs543.3 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
144.1 µs144 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
542 µs541.6 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
80 µs80 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
564.4 µs564.6 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
141.8 µs141.8 µs
Commits
Click on a commit to change the comparison rangeBase
main
d21e90f
-0.01%
fix(openai): gpt-5.5 does not support reasoning_effort=minimal
34c9364
4 months ago
by mateo-berri+0.22%
feat(openai): add supports_low_reasoning_effort flag; reject low on gpt-5.5-pro
94f8f12
4 months ago
by mateo-berri-0.13%
test: register supports_low_reasoning_effort in cost-map JSON schema
c333838
4 months ago
by mateo-berri