Comparing
joereyna:litellm_fix_responses_websocket_model_query_param
(c0999d3
) withmain
(fdd7500
)0%
- Untouched
- 16
Benchmarks
16 total
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
574.8 µs572.5 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
420.3 µs419.2 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
240.2 µs239.8 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
543.2 µs543.1 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.4 µs87.5 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
186.6 µs186.8 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
85.3 µs85.5 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
149 µs149.3 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
544.4 µs545.4 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
141.9 µs142.3 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
146.6 µs147.1 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.1 µs85.4 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
142.9 µs143.5 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-1%
88.2 µs89.4 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-2%
84.8 µs86.1 µs
Commits
Click on a commit to change the comparison rangeBase
main
fdd7500
+0.25%
route OpenAI responses WebSocket through managed HTTP path
7dd09da
7 days ago
by joereyna-0.56%
add openai_responses_native_websocket opt-in flag
4dacde3
7 days ago
by joereyna+0.07%
remove redundant litellm import in supports_native_websocket
c0999d3
5 days ago
by joereyna