diff --git a/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py b/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py index 106074811f6..4e6f4a2a51a 100644 --- a/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py +++ b/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py @@ -228,11 +228,17 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig): Gemini 3 models include: - gemini-3-pro-preview + - gemini-3-flash + - skyhawk (Gemini 3 Flash checkpoint) - Any future Gemini 3.x models """ # Check for Gemini 3 models if "gemini-3" in model: return True + + # Check for skyhawk (Gemini 3 Flash checkpoint) + if "skyhawk" in model.lower(): + return True return False @@ -626,22 +632,40 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig): Returns: GeminiThinkingConfig with thinkingLevel and includeThoughts """ + # Check if this is skyhawk/gemini-3-flash which supports MINIMAL thinking level + is_skyhawk = model and ( + "skyhawk" in model.lower() or "gemini-3-flash" in model.lower() + ) if reasoning_effort == "minimal": - return {"thinkingLevel": "low", "includeThoughts": True} + if is_skyhawk: + return {"thinkingLevel": "minimal", "includeThoughts": True} + else: + return {"thinkingLevel": "low", "includeThoughts": True} elif reasoning_effort == "low": return {"thinkingLevel": "low", "includeThoughts": True} elif reasoning_effort == "medium": - return { - "thinkingLevel": "high", - "includeThoughts": True, - } # medium is not out yet + # For skyhawk, medium maps to "medium", otherwise "high" + if is_skyhawk: + return {"thinkingLevel": "medium", "includeThoughts": True} + else: + return { + "thinkingLevel": "high", + "includeThoughts": True, + } # medium is not out yet for other models elif reasoning_effort == "high": return {"thinkingLevel": "high", "includeThoughts": True} elif reasoning_effort == "disable": - # Gemini 3 cannot fully disable thinking, so we use "low" but hide thoughts - return {"thinkingLevel": "low", "includeThoughts": False} + # Gemini 3 cannot fully disable thinking, so we use "minimal" for skyhawk, "low" for others + if is_skyhawk: + return {"thinkingLevel": "minimal", "includeThoughts": False} + else: + return {"thinkingLevel": "low", "includeThoughts": False} elif reasoning_effort == "none": - return {"thinkingLevel": "low", "includeThoughts": False} + # For skyhawk, use "minimal" instead of "low" + if is_skyhawk: + return {"thinkingLevel": "minimal", "includeThoughts": False} + else: + return {"thinkingLevel": "low", "includeThoughts": False} else: raise ValueError(f"Invalid reasoning effort: {reasoning_effort}") @@ -911,7 +935,10 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig): "thinkingLevel" not in thinking_config and "thinkingBudget" not in thinking_config ): - thinking_config["thinkingLevel"] = "low" + # For skyhawk, default to "minimal" to match Gemini 2.5 Flash behavior + # For other Gemini 3 models, default to "low" + is_skyhawk = "skyhawk" in model.lower() or "gemini-3-flash" in model.lower() + thinking_config["thinkingLevel"] = "minimal" if is_skyhawk else "low" optional_params["thinkingConfig"] = thinking_config return optional_params diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 79a6d2de06a..ff99f1ea728 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -14416,6 +14416,98 @@ "supports_web_search": true, "tpm": 800000 }, + "gemini/skyhawk": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "rpm": 2000, + "source": "https://ai.google.dev/gemini-api/docs/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000 + }, + "skyhawk": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true + }, "gemini/gemini-2.5-pro-exp-03-25": { "cache_read_input_token_cost": 0.0, "input_cost_per_token": 0.0, diff --git a/litellm/types/llms/vertex_ai.py b/litellm/types/llms/vertex_ai.py index e4c5360ae3b..6a3dfb74ce1 100644 --- a/litellm/types/llms/vertex_ai.py +++ b/litellm/types/llms/vertex_ai.py @@ -176,7 +176,7 @@ class SafetSettingsConfig(TypedDict, total=False): class GeminiThinkingConfig(TypedDict, total=False): includeThoughts: bool thinkingBudget: int - thinkingLevel: Literal["low", "medium", "high"] + thinkingLevel: Literal["minimal", "low", "medium", "high"] GeminiResponseModalities = Literal["TEXT", "IMAGE", "AUDIO", "VIDEO"] diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 79a6d2de06a..ff99f1ea728 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -14416,6 +14416,98 @@ "supports_web_search": true, "tpm": 800000 }, + "gemini/skyhawk": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "rpm": 2000, + "source": "https://ai.google.dev/gemini-api/docs/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000 + }, + "skyhawk": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true + }, "gemini/gemini-2.5-pro-exp-03-25": { "cache_read_input_token_cost": 0.0, "input_cost_per_token": 0.0,