diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index d43eda39b1f..f577406fc68 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -45890,6 +45890,7 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -45915,6 +45916,7 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -45940,6 +45942,7 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -45999,6 +46002,7 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 749b2566c2a..af69d58f00a 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -46012,6 +46012,7 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -46037,6 +46038,7 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -46062,6 +46064,7 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -46087,6 +46090,7 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, diff --git a/tests/e2e/llm_translation/test_chat_completions_regression_e2e.py b/tests/e2e/llm_translation/test_chat_completions_regression_e2e.py index af0e782e224..35be2254273 100644 --- a/tests/e2e/llm_translation/test_chat_completions_regression_e2e.py +++ b/tests/e2e/llm_translation/test_chat_completions_regression_e2e.py @@ -343,10 +343,14 @@ class TestHostedVllmChat: def test_hosted_vllm_chat_returns_content( self, client: PassthroughClient, resources: ResourceManager ) -> None: - api_base = os.environ["HOSTED_VLLM_API_BASE"] - api_key = (os.environ.get("HOSTED_VLLM_API_KEY") or "").strip() or None + api_base = os.environ.get("HOSTED_VLLM_API_BASE") + if api_base is None: + pytest.skip( + "set HOSTED_VLLM_API_BASE (the live vLLM server this deployment targets)" + ) backend = ( - os.environ.get("HOSTED_VLLM_MODEL") or "meta-llama/Llama-3.2-3B-Instruct" + os.environ.get("HOSTED_VLLM_MODEL") + or "Qwen/Qwen2.5-0.5B-Instruct-GGUF:Q4_K_M" ).strip() model = f"e2e-vllm-chat-{unique_marker()}" model_id = client.proxy.create_model( @@ -354,7 +358,6 @@ class TestHostedVllmChat: LiteLLMParamsBody( model=f"hosted_vllm/{backend}", api_base=api_base, - api_key=api_key, ), ) resources.defer(lambda: client.proxy.delete_model(model_id)) diff --git a/tests/e2e/llm_translation/test_deepseek_reasoning_e2e.py b/tests/e2e/llm_translation/test_deepseek_reasoning_e2e.py index b06b241c0b5..8dfccf0d74b 100644 --- a/tests/e2e/llm_translation/test_deepseek_reasoning_e2e.py +++ b/tests/e2e/llm_translation/test_deepseek_reasoning_e2e.py @@ -5,7 +5,7 @@ DeepSeek's reasoner defaults thinking ON and surfaces the chain as ``reasoning_effort="none"`` and ``thinking={"type": "disabled"}``. The DeepSeek param mapper (``litellm/llms/deepseek/chat/transformation.py`` ``map_openai_params``) forwards both as ``thinking={"type": "disabled"}`` so the -outbound body carries a real disable signal and ``deepseek-reasoner`` returns no +outbound body carries a real disable signal and the reasoning model returns no ``reasoning_content``. This is the behavior tracked by LIT-3686 / GH #27453. The control case proves the model and path work (reasoning is returned when @@ -27,7 +27,7 @@ from passthrough_client import PassthroughClient pytestmark = pytest.mark.e2e -REASONER = "deepseek/deepseek-reasoner" +REASONER = "deepseek/deepseek-v4-pro" PROMPT = "What is 17 + 26? Answer with just the number." @@ -67,7 +67,7 @@ class TestDeepSeekReasoningDisable: ) reasoning = _reasoning_content(response) assert reasoning, ( - "control case: deepseek-reasoner returned no reasoning_content with no " + "control case: the reasoning model returned no reasoning_content with no " f"disable param, so the disable assertions below can't be trusted: {response}" ) diff --git a/tests/e2e/llm_translation/test_embeddings_endpoint_e2e.py b/tests/e2e/llm_translation/test_embeddings_endpoint_e2e.py index 157caedd561..128913802e2 100644 --- a/tests/e2e/llm_translation/test_embeddings_endpoint_e2e.py +++ b/tests/e2e/llm_translation/test_embeddings_endpoint_e2e.py @@ -72,7 +72,7 @@ class TestEmbeddingsEndpoint: model_id = endpoints_client.create_model( model, LiteLLMParamsBody( - model="vertex_ai/gemini-embedding-2", + model="vertex_ai/text-embedding-005", vertex_project="os.environ/VERTEXAI_PROJECT", vertex_location="us-central1", ), diff --git a/tests/e2e/llm_translation/test_image_generation_e2e.py b/tests/e2e/llm_translation/test_image_generation_e2e.py index 45861d1e93a..f7c23e46581 100644 --- a/tests/e2e/llm_translation/test_image_generation_e2e.py +++ b/tests/e2e/llm_translation/test_image_generation_e2e.py @@ -54,7 +54,7 @@ class TestImageGeneration: model_id = endpoints_client.create_model( model, LiteLLMParamsBody( - model="bedrock/amazon.titan-image-generator-v2:0", + model="bedrock/amazon.nova-canvas-v1:0", aws_access_key_id="os.environ/AWS_ACCESS_KEY_ID", aws_secret_access_key="os.environ/AWS_SECRET_ACCESS_KEY", aws_region_name="os.environ/AWS_REGION", diff --git a/tests/e2e/llm_translation/test_rerank_e2e.py b/tests/e2e/llm_translation/test_rerank_e2e.py index c3614251e77..c9f58b2c03c 100644 --- a/tests/e2e/llm_translation/test_rerank_e2e.py +++ b/tests/e2e/llm_translation/test_rerank_e2e.py @@ -60,7 +60,7 @@ class TestRerank: model_id = endpoints_client.create_model( model, LiteLLMParamsBody( - model="bedrock/amazon.rerank-v1:0", + model="bedrock/arn:aws:bedrock:us-east-1::foundation-model/cohere.rerank-v3-5:0", aws_access_key_id="os.environ/AWS_ACCESS_KEY_ID", aws_secret_access_key="os.environ/AWS_SECRET_ACCESS_KEY", aws_region_name="os.environ/AWS_REGION",