diff --git a/internal/registry/model_definitions.go b/internal/registry/model_definitions.go index 8cf1f691..c94f2b6d 100644 --- a/internal/registry/model_definitions.go +++ b/internal/registry/model_definitions.go @@ -68,28 +68,13 @@ func GetClaudeModels() []*ModelInfo { } } -// GeminiModels returns the shared base Gemini model set used by multiple providers. -func GeminiModels() []*ModelInfo { +// GetGeminiModels returns the standard Gemini model definitions +func GetGeminiModels() []*ModelInfo { return []*ModelInfo{ - { - ID: "gemini-2.5-flash", - Object: "model", - Created: time.Now().Unix(), - OwnedBy: "google", - Type: "gemini", - Name: "models/gemini-2.5-flash", - Version: "001", - DisplayName: "Gemini 2.5 Flash", - Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.", - InputTokenLimit: 1048576, - OutputTokenLimit: 65536, - SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, - Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, - }, { ID: "gemini-2.5-pro", Object: "model", - Created: time.Now().Unix(), + Created: 1750118400, OwnedBy: "google", Type: "gemini", Name: "models/gemini-2.5-pro", @@ -101,10 +86,25 @@ func GeminiModels() []*ModelInfo { SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true}, }, + { + ID: "gemini-2.5-flash", + Object: "model", + Created: 1750118400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-2.5-flash", + Version: "001", + DisplayName: "Gemini 2.5 Flash", + Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, + }, { ID: "gemini-2.5-flash-lite", Object: "model", - Created: time.Now().Unix(), + Created: 1753142400, OwnedBy: "google", Type: "gemini", Name: "models/gemini-2.5-flash-lite", @@ -119,7 +119,7 @@ func GeminiModels() []*ModelInfo { { ID: "gemini-3-pro-preview", Object: "model", - Created: time.Now().Unix(), + Created: 1737158400, OwnedBy: "google", Type: "gemini", Name: "models/gemini-3-pro-preview", @@ -134,31 +134,12 @@ func GeminiModels() []*ModelInfo { } } -// GetGeminiModels returns the standard Gemini model definitions -func GetGeminiModels() []*ModelInfo { return GeminiModels() } - -// GetGeminiCLIModels returns the standard Gemini model definitions -func GetGeminiCLIModels() []*ModelInfo { +func GetGeminiVertexModels() []*ModelInfo { return []*ModelInfo{ - { - ID: "gemini-2.5-flash", - Object: "model", - Created: time.Now().Unix(), - OwnedBy: "google", - Type: "gemini", - Name: "models/gemini-2.5-flash", - Version: "001", - DisplayName: "Gemini 2.5 Flash", - Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.", - InputTokenLimit: 1048576, - OutputTokenLimit: 65536, - SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, - Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, - }, { ID: "gemini-2.5-pro", Object: "model", - Created: time.Now().Unix(), + Created: 1750118400, OwnedBy: "google", Type: "gemini", Name: "models/gemini-2.5-pro", @@ -170,10 +151,25 @@ func GetGeminiCLIModels() []*ModelInfo { SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true}, }, + { + ID: "gemini-2.5-flash", + Object: "model", + Created: 1750118400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-2.5-flash", + Version: "001", + DisplayName: "Gemini 2.5 Flash", + Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, + }, { ID: "gemini-2.5-flash-lite", Object: "model", - Created: time.Now().Unix(), + Created: 1753142400, OwnedBy: "google", Type: "gemini", Name: "models/gemini-2.5-flash-lite", @@ -188,7 +184,87 @@ func GetGeminiCLIModels() []*ModelInfo { { ID: "gemini-3-pro-preview", Object: "model", - Created: time.Now().Unix(), + Created: 1737158400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-3-pro-preview", + Version: "3.0", + DisplayName: "Gemini 3 Pro Preview", + Description: "Gemini 3 Pro Preview", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true}, + }, + { + ID: "gemini-3-pro-image-preview", + Object: "model", + Created: 1737158400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-3-pro-image-preview", + Version: "3.0", + DisplayName: "Gemini 3 Pro Image Preview", + Description: "Gemini 3 Pro Image Preview", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + }, + } +} + +// GetGeminiCLIModels returns the standard Gemini model definitions +func GetGeminiCLIModels() []*ModelInfo { + return []*ModelInfo{ + { + ID: "gemini-2.5-pro", + Object: "model", + Created: 1750118400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-2.5-pro", + Version: "2.5", + DisplayName: "Gemini 2.5 Pro", + Description: "Stable release (June 17th, 2025) of Gemini 2.5 Pro", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true}, + }, + { + ID: "gemini-2.5-flash", + Object: "model", + Created: 1750118400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-2.5-flash", + Version: "001", + DisplayName: "Gemini 2.5 Flash", + Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, + }, + { + ID: "gemini-2.5-flash-lite", + Object: "model", + Created: 1753142400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-2.5-flash-lite", + Version: "2.5", + DisplayName: "Gemini 2.5 Flash Lite", + Description: "Our smallest and most cost effective model, built for at scale usage.", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, + }, + { + ID: "gemini-3-pro-preview", + Object: "model", + Created: 1737158400, OwnedBy: "google", Type: "gemini", Name: "models/gemini-3-pro-preview", @@ -205,87 +281,143 @@ func GetGeminiCLIModels() []*ModelInfo { // GetAIStudioModels returns the Gemini model definitions for AI Studio integrations func GetAIStudioModels() []*ModelInfo { - base := GeminiModels() - - return append(base, - []*ModelInfo{ - { - ID: "gemini-pro-latest", - Object: "model", - Created: time.Now().Unix(), - OwnedBy: "google", - Type: "gemini", - Name: "models/gemini-pro-latest", - Version: "2.5", - DisplayName: "Gemini Pro Latest", - Description: "Latest release of Gemini Pro", - InputTokenLimit: 1048576, - OutputTokenLimit: 65536, - SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, - Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true}, - }, - { - ID: "gemini-flash-latest", - Object: "model", - Created: time.Now().Unix(), - OwnedBy: "google", - Type: "gemini", - Name: "models/gemini-flash-latest", - Version: "2.5", - DisplayName: "Gemini Flash Latest", - Description: "Latest release of Gemini Flash", - InputTokenLimit: 1048576, - OutputTokenLimit: 65536, - SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, - Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, - }, - { - ID: "gemini-flash-lite-latest", - Object: "model", - Created: time.Now().Unix(), - OwnedBy: "google", - Type: "gemini", - Name: "models/gemini-flash-lite-latest", - Version: "2.5", - DisplayName: "Gemini Flash-Lite Latest", - Description: "Latest release of Gemini Flash-Lite", - InputTokenLimit: 1048576, - OutputTokenLimit: 65536, - SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, - Thinking: &ThinkingSupport{Min: 512, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, - }, - { - ID: "gemini-2.5-flash-image-preview", - Object: "model", - Created: time.Now().Unix(), - OwnedBy: "google", - Type: "gemini", - Name: "models/gemini-2.5-flash-image-preview", - Version: "2.5", - DisplayName: "Gemini 2.5 Flash Image Preview", - Description: "State-of-the-art image generation and editing model.", - InputTokenLimit: 1048576, - OutputTokenLimit: 8192, - SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, - // image models don't support thinkingConfig; leave Thinking nil - }, - { - ID: "gemini-2.5-flash-image", - Object: "model", - Created: time.Now().Unix(), - OwnedBy: "google", - Type: "gemini", - Name: "models/gemini-2.5-flash-image", - Version: "2.5", - DisplayName: "Gemini 2.5 Flash Image", - Description: "State-of-the-art image generation and editing model.", - InputTokenLimit: 1048576, - OutputTokenLimit: 8192, - SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, - // image models don't support thinkingConfig; leave Thinking nil - }, - }..., - ) + return []*ModelInfo{ + { + ID: "gemini-2.5-pro", + Object: "model", + Created: 1750118400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-2.5-pro", + Version: "2.5", + DisplayName: "Gemini 2.5 Pro", + Description: "Stable release (June 17th, 2025) of Gemini 2.5 Pro", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true}, + }, + { + ID: "gemini-2.5-flash", + Object: "model", + Created: 1750118400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-2.5-flash", + Version: "001", + DisplayName: "Gemini 2.5 Flash", + Description: "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, + }, + { + ID: "gemini-2.5-flash-lite", + Object: "model", + Created: 1753142400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-2.5-flash-lite", + Version: "2.5", + DisplayName: "Gemini 2.5 Flash Lite", + Description: "Our smallest and most cost effective model, built for at scale usage.", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, + }, + { + ID: "gemini-3-pro-preview", + Object: "model", + Created: 1737158400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-3-pro-preview", + Version: "3.0", + DisplayName: "Gemini 3 Pro Preview", + Description: "Gemini 3 Pro Preview", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true}, + }, + { + ID: "gemini-pro-latest", + Object: "model", + Created: 1750118400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-pro-latest", + Version: "2.5", + DisplayName: "Gemini Pro Latest", + Description: "Latest release of Gemini Pro", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true}, + }, + { + ID: "gemini-flash-latest", + Object: "model", + Created: 1750118400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-flash-latest", + Version: "2.5", + DisplayName: "Gemini Flash Latest", + Description: "Latest release of Gemini Flash", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, + }, + { + ID: "gemini-flash-lite-latest", + Object: "model", + Created: 1753142400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-flash-lite-latest", + Version: "2.5", + DisplayName: "Gemini Flash-Lite Latest", + Description: "Latest release of Gemini Flash-Lite", + InputTokenLimit: 1048576, + OutputTokenLimit: 65536, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + Thinking: &ThinkingSupport{Min: 512, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, + }, + { + ID: "gemini-2.5-flash-image-preview", + Object: "model", + Created: 1756166400, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-2.5-flash-image-preview", + Version: "2.5", + DisplayName: "Gemini 2.5 Flash Image Preview", + Description: "State-of-the-art image generation and editing model.", + InputTokenLimit: 1048576, + OutputTokenLimit: 8192, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + // image models don't support thinkingConfig; leave Thinking nil + }, + { + ID: "gemini-2.5-flash-image", + Object: "model", + Created: 1759363200, + OwnedBy: "google", + Type: "gemini", + Name: "models/gemini-2.5-flash-image", + Version: "2.5", + DisplayName: "Gemini 2.5 Flash Image", + Description: "State-of-the-art image generation and editing model.", + InputTokenLimit: 1048576, + OutputTokenLimit: 8192, + SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"}, + // image models don't support thinkingConfig; leave Thinking nil + }, + } } // GetOpenAIModels returns the standard OpenAI model definitions diff --git a/sdk/cliproxy/service.go b/sdk/cliproxy/service.go index d5f670d9..04982cfe 100644 --- a/sdk/cliproxy/service.go +++ b/sdk/cliproxy/service.go @@ -629,7 +629,7 @@ func (s *Service) registerModelsForAuth(a *coreauth.Auth) { models = registry.GetGeminiModels() case "vertex": // Vertex AI Gemini supports the same model identifiers as Gemini. - models = registry.GetGeminiModels() + models = registry.GetGeminiVertexModels() case "gemini-cli": models = registry.GetGeminiCLIModels() case "aistudio":