Comparing
awais786:fix/tool-result-images-gemini
(41f3282
) withlitellm_oss_staging_03_17_2026
(58e74a6
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py+2%
88.1 µs86.1 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+1%
89.4 µs88.5 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py+1%
572.5 µs568.7 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+1%
86 µs85.5 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
419.2 µs417.8 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
188.1 µs187.7 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
239.6 µs239.4 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
544.7 µs544.3 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
542.5 µs543.5 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
146.7 µs147 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
143.4 µs143.6 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
149.3 µs149.7 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
141.9 µs142.5 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py-1%
85.2 µs85.9 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py-1%
87.5 µs88.3 µs
Commits
Click on a commit to change the comparison rangeBase
main
58e74a6
-0.17%
fix(gemini): support images in tool_results for /v1/messages routing
f13bc75
1 month ago
by awais786+0.49%
fix(gemini): support images in tool_results for /v1/messages routing
9e7397e
1 month ago
by awais786+0.19%
fix(gemini): support images in tool_results for /v1/messages routing
c565e09
1 month ago
by awais786-0.36%
fix(fireworks): skip #transform=inline for base64 data URLs
41f3282
1 month ago
by awais786