Comparing
litellm_fix-llm-provider-inference-for-unprefixed-models
(ee885f1
) withmain
(62757ff
)0%
- Untouched
- 16
Benchmarks
16 total
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py+1%
1.7 ms1.7 ms
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
573.7 µs571.6 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
239.2 µs238.4 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
187.2 µs186.8 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
415.9 µs415.2 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.1 µs85 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
544.8 µs544.5 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
544.9 µs544.8 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.4 µs87.4 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
85.2 µs85.5 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-1%
84.7 µs85.2 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-1%
87.2 µs87.9 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-2%
141.7 µs143.9 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py-2%
148.8 µs151.2 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py-2%
142.8 µs145.3 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py-2%
146.2 µs148.9 µs
Commits
Click on a commit to change the comparison rangeBase
main
62757ff
-0.36%
fix(router): pass custom_llm_provider to get_llm_provider for unprefixed model names
ee885f1
9 days ago
by Sameerlite