chore(tests): add read-only VCR cassette episode-diff diagnostic
#28795Comparing
claude/gpt-image-1-costs-hYxer
(7d7e0b7
) withlitellm_internal_staging
(3bcfe41
)-1%
- Untouched
- 16
Benchmarks
16 total
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py-2%
144.1 µs146.6 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py-2%
1.7 ms1.7 ms
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-2%
137.2 µs139.4 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py-1%
234.8 µs237.5 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py-1%
183.4 µs185.4 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-1%
81.3 µs82.2 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py-1%
555 µs560.1 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-1%
80.4 µs81.1 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py-1%
557.5 µs561.9 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py-1%
412.8 µs416 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py-1%
562.2 µs565.1 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.4 µs82.1 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
80.1 µs80 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
142.1 µs141.9 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.3 µs138.1 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
80.1 µs80.1 µs
Commits
Click on a commit to change the comparison rangeBase
litellm_internal_staging
3bcfe41
-0.7%
chore(tests): add read-only VCR cassette episode-diff diagnostic
7d7e0b7
3 months ago
by claude