Comparing
litellm_internal_staging
(c2c2a62
) withmain
(16f6d92
)0%
- Untouched
- 31
No successful run was found on main ( c2c2a62) during the generation of this report, so 16f6d92 was used instead as the comparison base. There might be some changes unrelated to this pull request in this report.
Benchmarks
31 total
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py-1%
199.4 µs202 µs
test_mcp_server_strip_prefix_on_call
tests/benchmarks/test_mcp_benchmarks.py-1%
83.7 µs84.8 µs
test_logging_executor_runs_inline
tests/benchmarks/test_benchmarks.py+1%
126.7 µs125.6 µs
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.py-1%
603.2 µs607.6 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-1%
140.5 µs141.4 µs
test_a2a_inbound_message_to_openai_messages
tests/benchmarks/test_a2a_benchmarks.py-1%
104.8 µs105.5 µs
test_convert_messages_to_a2a_prompt
tests/benchmarks/test_a2a_benchmarks.py-1%
110.9 µs111.7 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py-1%
79.9 µs80.4 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py-1%
146.9 µs147.7 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-1%
81.5 µs82 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-1%
81.3 µs81.8 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
80.5 µs80.9 µs
test_extract_text_from_a2a_message_response
tests/benchmarks/test_a2a_benchmarks.py0%
87.6 µs88 µs
test_extract_text_from_a2a_task_response
tests/benchmarks/test_a2a_benchmarks.py0%
87.8 µs88.2 µs
test_response_to_model_response_object
tests/benchmarks/test_inference_benchmarks.py0%
400.8 µs399.1 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
586.6 µs589.1 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
149.2 µs149.7 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82.6 µs82.9 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
144.7 µs145.2 µs
test_completion_with_tools
tests/benchmarks/test_inference_benchmarks.py0%
3.7 ms3.7 ms
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
239.9 µs240.7 µs
test_transform_single_mcp_tool_to_openai
tests/benchmarks/test_mcp_benchmarks.py0%
89.5 µs89.8 µs
test_completion_streaming
tests/benchmarks/test_inference_benchmarks.py0%
39.2 ms39.3 ms
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
588.6 µs590.1 µs
Commits
Click on a commit to change the comparison rangeBase
main
af6dc1d
+0.07%
Merge pull request #36363 from joshgarnett/bugfix/responses-reasoning-object-to-effort
67dd150
2 months ago
by ryan-crabbe-berri-0.21%
fix(proxy): bound tool and guardrail index create_many by the spend-log statement budgets (#40561)
5604550
2 months ago
by devin-ai-integration[bot]-0.02%
Merge pull request #40912 from BerriAI/litellm_logging_worker_timeout_summary
e240997
2 months ago
by mateo-berri+0.18%
Merge pull request #40929 from BerriAI/litellm_fireworks_short_key_lookup
9ae727b
2 months ago
by kerry-berri-0.16%
Merge pull request #40172 from BerriAI/litellm_remove_main_guard
daa2b02
2 months ago
by yuneng-berri-0.01%
Merge pull request #39846 from BerriAI/litellm_bedrock_mantle_govcloud_cost_row
c2c2a62
2 months ago
by mateo-berri+0.13%
Merge pull request #40107 from BerriAI/litellm_forced_password_reset
b3882d8
2 months ago
by ojensen-berri+0.14%
Merge pull request #41058 from BerriAI/litellm_fix_wrapper_async_double_sync_success_handler
1f8bae7
2 months ago
by yassin-berriai-0.26%
Merge pull request #37762 from BerriAI/litellm_model_hub_description
3f32a19
2 months ago
by ryan-crabbe-berri+0.3%
Merge pull request #40993 from BerriAI/litellm_health_check_skip_save_on_failed_read
af6dc1d
2 months ago
by yassin-berriai-0.04%
Merge pull request #34939 from BerriAI/litellm_dd_span_user_email
252c71c
2 months ago
by yassin-berriai