Comparing
Chesars:fix/responses-api-gpt5-temperature-drop-params
(bfee7f0
) withlitellm_staging_03_22_2026
(c89496f
)0%
- Untouched
- 16
Benchmarks
16 total
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py+2%
1.7 ms1.7 ms
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py+2%
86.9 µs85.5 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py-1%
415.9 µs419.7 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+1%
88.2 µs87.5 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py+1%
189.2 µs187.7 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py+1%
544.6 µs541.3 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-1%
84.1 µs84.6 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
239.5 µs240.4 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.7 µs87.4 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
148.8 µs149.2 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
567.6 µs568.9 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.4 µs85.2 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
143.4 µs143.2 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
142 µs141.9 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
542.9 µs543.1 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
146.3 µs146.4 µs
Commits
Click on a commit to change the comparison rangeBase
main
c89496f
+0.1%
fix(responses-api): apply GPT-5 temperature validation in Responses API
fff83dd
5 months ago
by Chesars+0.22%
test: add supports_none branch coverage for Responses API GPT-5 temperature
f8a9bbd
5 months ago
by Chesars-0.06%
fix: improve error message for supports-none models with temperature
bfee7f0
5 months ago
by Chesars