Comparing
litellm_internal_staging
(68d6721
) withlitellm_oss_staging
(fc7538f
)0%
- Untouched
- 16
This run is associated to a commit that was force-pushed
It will not be associated with its branch history. Be careful when comparing its performance to other runs.Benchmarks
16 total
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+2%
82.3 µs80.8 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+1%
82.8 µs81.9 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py-1%
1.7 ms1.7 ms
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py+1%
236.5 µs235.1 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.9 µs80.2 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.1 µs82.5 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
183.7 µs184.3 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
143.6 µs143.1 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
139.9 µs139.4 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
564.7 µs563 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
79.9 µs80.1 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
137.6 µs137.3 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
144.7 µs144.5 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
563 µs563.8 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
567.9 µs568.6 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
415.4 µs415.2 µs
Commits
Click on a commit to change the comparison rangeBase
main
fc7538f
+0.14%
fix: 400 on Anthropic context overflow; seed identity on failed auth (#29848)
68d6721
11 days ago
by yassin-berriai