diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 773ffb92b59..a6f59abc140 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -18747,6 +18747,49 @@ }, "supports_image_size": false }, + "gemini/gemini-3-pro-image": { + "input_cost_per_image": 0.0011, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "gemini", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.134, + "output_cost_per_image_token": 0.00012, + "output_cost_per_token": 1.2e-05, + "rpm": 1000, + "tpm": 4000000, + "output_cost_per_token_batches": 6e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query" + }, "gemini/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -18778,6 +18821,49 @@ ], "supports_function_calling": false, "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query" + }, + "gemini/gemini-3.1-flash-image": { + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "litellm_provider": "gemini", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.045, + "output_cost_per_image_token": 6e-05, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "rpm": 1000, + "tpm": 4000000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, @@ -18819,6 +18905,7 @@ ], "supports_function_calling": false, "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, @@ -36777,6 +36864,7 @@ "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -36786,6 +36874,22 @@ "tpm": 8000000, "supports_image_size": false }, + "vertex_ai/gemini-3-pro-image": { + "input_cost_per_image": 0.0011, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.134, + "output_cost_per_image_token": 0.00012, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_batches": 6e-06, + "supports_reasoning": false, + "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" + }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -36799,8 +36903,23 @@ "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, + "supports_reasoning": false, "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" }, + "vertex_ai/gemini-3.1-flash-image": { + "input_cost_per_image": 0.00056, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0672, + "output_cost_per_image_token": 6e-05, + "output_cost_per_token": 3e-06, + "supports_reasoning": false, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" + }, "vertex_ai/gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-07, @@ -36812,6 +36931,7 @@ "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, "output_cost_per_token": 3e-06, + "supports_reasoning": false, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, "vertex_ai/gemini-3.1-flash-lite-preview": { diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 6a770998331..08a452be844 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -18865,7 +18865,8 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "supports_reasoning": false }, "gemini/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -18898,6 +18899,7 @@ ], "supports_function_calling": false, "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, @@ -18939,6 +18941,7 @@ ], "supports_function_calling": false, "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, @@ -18980,6 +18983,7 @@ ], "supports_function_calling": false, "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, @@ -36951,6 +36955,7 @@ "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -36973,6 +36978,7 @@ "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, + "supports_reasoning": false, "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" }, "vertex_ai/gemini-3-pro-image-preview": { @@ -36988,6 +36994,7 @@ "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, + "supports_reasoning": false, "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" }, "vertex_ai/gemini-3.1-flash-image": { @@ -37001,6 +37008,7 @@ "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, "output_cost_per_token": 3e-06, + "supports_reasoning": false, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, "vertex_ai/gemini-3.1-flash-image-preview": { @@ -37014,6 +37022,7 @@ "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, "output_cost_per_token": 3e-06, + "supports_reasoning": false, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, "vertex_ai/gemini-3.1-flash-lite-preview": { diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index 26ae6ff7f4c..1a5c419754b 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -4710,3 +4710,30 @@ class TestValidateEnvironmentTencent: assert "TENCENT_API_KEY" in result["missing_keys"] + +@pytest.mark.parametrize( + "model", + [ + "vertex_ai/gemini-2.5-flash-image", + "vertex_ai/gemini-3-pro-image", + "vertex_ai/gemini-3-pro-image-preview", + "vertex_ai/gemini-3.1-flash-image", + "vertex_ai/gemini-3.1-flash-image-preview", + "gemini/gemini-2.5-flash-image", + "gemini/gemini-3-pro-image", + "gemini/gemini-3-pro-image-preview", + "gemini/gemini-3.1-flash-image", + "gemini/gemini-3.1-flash-image-preview", + ], +) +def test_gemini_image_models_do_not_support_reasoning( + model: str, local_model_cost_map: None +) -> None: + assert model in litellm.model_cost, ( + f"{model} is missing from the local model cost map. " + "Add its entry to litellm/model_prices_and_context_window_backup.json." + ) + assert litellm.supports_reasoning(model) is False, ( + f"{model} incorrectly classified as reasoning-capable. " + "Add 'supports_reasoning: false' to its model_cost entry." + )