Bedrock: move native structured output model list to cost JSON, add Sonnet 4.6
#23794Comparing
ndgigliotti:feat/bedrock-structured-output-cost-json
(a536bfd
) withmain
(e6e3085
)0%
- Untouched
- 16
Benchmarks
16 total
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.py0%
571.1 µs568.3 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
543.7 µs542.1 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
416 µs415.1 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
239.1 µs238.8 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
142.9 µs143 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
186.3 µs186.4 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
85.4 µs85.5 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
541.2 µs542 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
84.9 µs85 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
141.5 µs141.9 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.1 µs87.5 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
148.6 µs149.2 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py-1%
146.1 µs147.1 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-1%
83.6 µs84.7 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-1%
86.5 µs87.7 µs
Commits
Click on a commit to change the comparison rangeBase
main
e6e3085
-0.17%
Keep multimodal gemini-embedding-2-preview entry to align with #23599
a536bfd
4 days ago
by ndgigliotti