Comparing
litellm_anthropic-messages-thinking-signature-retry
(5670f6c
) withlitellm_ishaan_april14
(e64d98f
)0%
- Untouched
- 16
Benchmarks
16 total
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py+2%
1.7 ms1.7 ms
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py-1%
81.3 µs82.4 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py-1%
141.7 µs143.1 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py+1%
236.6 µs234.6 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py+1%
568.4 µs563.6 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py+1%
413.1 µs410.3 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py+1%
183.9 µs182.8 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
137.4 µs136.7 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.1 µs81.7 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.8 µs79.5 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
541.8 µs543.4 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
144.4 µs144 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
540.8 µs542.1 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.1 µs137.9 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
81.6 µs81.7 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py0%
81.3 µs81.4 µs
Commits
Click on a commit to change the comparison rangeBase
main
e64d98f
+0.22%
feat(anthropic): retry /v1/messages after invalid thinking signature
c7f7708
4 months ago
by Sameerlite0%
fix(anthropic): tighten thinking-signature retry (Greptile)
5670f6c
4 months ago
by Sameerlite