From b6cdb27f44652b4b3f9a1d421bee1d7923022c5b Mon Sep 17 00:00:00 2001 From: mateo Date: Wed, 12 Aug 2026 21:32:06 +0000 Subject: [PATCH] test(bedrock_mantle): pin GPT-5.6 1M context window and long-context rates Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../test_bedrock_mantle_responses_transformation.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py b/tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py index a47a56376a4..8281f3387d9 100644 --- a/tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py +++ b/tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py @@ -1526,7 +1526,11 @@ class TestBedrockMantleResponsesPricing: assert info["cache_creation_input_token_cost"] == pytest.approx(cache_creation_cost) assert info["cache_read_input_token_cost"] == pytest.approx(cache_read_cost) assert info["output_cost_per_token"] == pytest.approx(output_cost) - assert info["max_input_tokens"] == 272000 + assert info["max_input_tokens"] == 1000000 + assert info["input_cost_per_token_above_272k_tokens"] == pytest.approx(input_cost * 2) + assert info["cache_creation_input_token_cost_above_272k_tokens"] == pytest.approx(cache_creation_cost * 2) + assert info["cache_read_input_token_cost_above_272k_tokens"] == pytest.approx(cache_read_cost * 2) + assert info["output_cost_per_token_above_272k_tokens"] == pytest.approx(output_cost * 1.5) @pytest.mark.parametrize( "model, input_cost, output_cost",