claude/busy-edison-90ZbL - Branch - BerriAI/litellm

fix(azure): preserve AD token refresh in v1 OpenAI client path

#28625

Merging

claude/busy-edison-90ZbL

into

litellm_internal_staging

N/A

New: 16

Benchmarks

16 total

test_cost_per_token_anthropic

tests/benchmarks/test_benchmarks.py

N/A

N/A557.2 µs

test_cost_per_token_openai

tests/benchmarks/test_benchmarks.py

N/A

N/A556.7 µs

test_get_llm_provider_anthropic

tests/benchmarks/test_benchmarks.py

N/A

N/A142.6 µs

test_get_model_info_with_provider

tests/benchmarks/test_benchmarks.py

N/A

N/A80 µs

test_get_llm_provider_azure

tests/benchmarks/test_benchmarks.py

N/A

N/A144.2 µs

test_token_counter_long_content

tests/benchmarks/test_benchmarks.py

N/A

N/A1.7 ms

test_token_counter_with_tools

tests/benchmarks/test_benchmarks.py

N/A

N/A415 µs

test_token_counter_multi_turn

tests/benchmarks/test_benchmarks.py

N/A

N/A566.5 µs

test_get_llm_provider_openai

tests/benchmarks/test_benchmarks.py

N/A

N/A139.4 µs

test_get_llm_provider_with_prefix

tests/benchmarks/test_benchmarks.py

N/A

N/A137.2 µs

test_token_counter_raw_text

tests/benchmarks/test_benchmarks.py

N/A

N/A183.8 µs

test_get_model_cost_key_case_insensitive

tests/benchmarks/test_benchmarks.py

N/A

N/A82.2 µs

test_token_counter_simple_message

tests/benchmarks/test_benchmarks.py

N/A

N/A237.2 µs

test_get_model_cost_key_exact_match

tests/benchmarks/test_benchmarks.py

N/A

N/A80 µs

test_get_model_info_anthropic

tests/benchmarks/test_benchmarks.py

N/A

N/A79.2 µs

test_get_model_info_openai

tests/benchmarks/test_benchmarks.py

N/A

N/A82.3 µs

Commits

Click on a commit to change the comparison range

No baseline data is yet availableOnce your main branch has generated a first performance report, you will see the list of commits and their performance impact here.

Home Terms Privacy Docs