Comparing
Dotify71:feat/anthropic-compaction-usage
(6beb5c8
) withlitellm_oss_staging_150626
(934ecdc
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-2%
78.8 µs80.2 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py-1%
143.8 µs145.6 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py+1%
81 µs80.3 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py-1%
540.8 µs544.2 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py-1%
82.2 µs82.7 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py-1%
234.6 µs235.9 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py-1%
141.8 µs142.5 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py+1%
1.7 ms1.7 ms
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
183.5 µs184.2 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
413.4 µs411.8 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.8 µs80 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
566.7 µs568.3 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.2 µs138.6 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
541 µs542.3 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
136.7 µs137 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
80.9 µs80.9 µs
Commits
Click on a commit to change the comparison rangeBase
main
934ecdc
-0.33%
feat(anthropic): surface compaction usage iterations data
6beb5c8
4 months ago
by Dotify71