**refactor(translator): remove service_tier from Codex OpenAI request payload**

feat(iflow): add cookie-based authentication endpoint

internal/api/handlers/management/auth_files.go

@@ -1443,6 +1443,87 @@ func (h *Handler) RequestIFlowToken(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{"status": "ok", "url": authURL, "state": state})
 }
 
+func (h *Handler) RequestIFlowCookieToken(c *gin.Context) {
+	ctx := context.Background()
+
+	var payload struct {
+		Cookie string `json:"cookie"`
+	}
+	if err := c.ShouldBindJSON(&payload); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"status": "error", "error": "cookie is required"})
+		return
+	}
+
+	cookieValue := strings.TrimSpace(payload.Cookie)
+
+	if cookieValue == "" {
+		c.JSON(http.StatusBadRequest, gin.H{"status": "error", "error": "cookie is required"})
+		return
+	}
+
+	cookieValue, errNormalize := iflowauth.NormalizeCookie(cookieValue)
+	if errNormalize != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"status": "error", "error": errNormalize.Error()})
+		return
+	}
+
+	authSvc := iflowauth.NewIFlowAuth(h.cfg)
+	tokenData, errAuth := authSvc.AuthenticateWithCookie(ctx, cookieValue)
+	if errAuth != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"status": "error", "error": errAuth.Error()})
+		return
+	}
+
+	tokenData.Cookie = cookieValue
+
+	tokenStorage := authSvc.CreateCookieTokenStorage(tokenData)
+	email := strings.TrimSpace(tokenStorage.Email)
+	if email == "" {
+		c.JSON(http.StatusBadRequest, gin.H{"status": "error", "error": "failed to extract email from token"})
+		return
+	}
+
+	fileName := iflowauth.SanitizeIFlowFileName(email)
+	if fileName == "" {
+		fileName = fmt.Sprintf("iflow-%d", time.Now().UnixMilli())
+	}
+
+	tokenStorage.Email = email
+
+	record := &coreauth.Auth{
+		ID:       fmt.Sprintf("iflow-%s.json", fileName),
+		Provider: "iflow",
+		FileName: fmt.Sprintf("iflow-%s.json", fileName),
+		Storage:  tokenStorage,
+		Metadata: map[string]any{
+			"email":        email,
+			"api_key":      tokenStorage.APIKey,
+			"expired":      tokenStorage.Expire,
+			"cookie":       tokenStorage.Cookie,
+			"type":         tokenStorage.Type,
+			"last_refresh": tokenStorage.LastRefresh,
+		},
+		Attributes: map[string]string{
+			"api_key": tokenStorage.APIKey,
+		},
+	}
+
+	savedPath, errSave := h.saveTokenRecord(ctx, record)
+	if errSave != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"status": "error", "error": "failed to save authentication tokens"})
+		return
+	}
+
+	fmt.Printf("iFlow cookie authentication successful. Token saved to %s\n", savedPath)
+	c.JSON(http.StatusOK, gin.H{
+		"status":     "ok",
+		"saved_path": savedPath,
+		"email":      email,
+		"expired":    tokenStorage.Expire,
+		"type":       tokenStorage.Type,
+	})
+}
+
 type projectSelectionRequiredError struct{}
 
 func (e *projectSelectionRequiredError) Error() string {

internal/api/server.go

@@ -518,6 +518,7 @@ func (s *Server) registerManagementRoutes() {
 		mgmt.GET("/gemini-cli-auth-url", s.mgmt.RequestGeminiCLIToken)
 		mgmt.GET("/qwen-auth-url", s.mgmt.RequestQwenToken)
 		mgmt.GET("/iflow-auth-url", s.mgmt.RequestIFlowToken)
+		mgmt.POST("/iflow-auth-url", s.mgmt.RequestIFlowCookieToken)
 		mgmt.GET("/get-auth-status", s.mgmt.GetAuthStatus)
 	}
 }

internal/auth/iflow/cookie_helpers.go

@@ -0,0 +1,38 @@
+package iflow
+
+import (
+	"fmt"
+	"strings"
+)
+
+// NormalizeCookie normalizes raw cookie strings for iFlow authentication flows.
+func NormalizeCookie(raw string) (string, error) {
+	trimmed := strings.TrimSpace(raw)
+	if trimmed == "" {
+		return "", fmt.Errorf("cookie cannot be empty")
+	}
+
+	combined := strings.Join(strings.Fields(trimmed), " ")
+	if !strings.HasSuffix(combined, ";") {
+		combined += ";"
+	}
+	if !strings.Contains(combined, "BXAuth=") {
+		return "", fmt.Errorf("cookie missing BXAuth field")
+	}
+	return combined, nil
+}
+
+// SanitizeIFlowFileName normalizes user identifiers for safe filename usage.
+func SanitizeIFlowFileName(raw string) string {
+	if raw == "" {
+		return ""
+	}
+	cleanEmail := strings.ReplaceAll(raw, "*", "x")
+	var result strings.Builder
+	for _, r := range cleanEmail {
+		if (r >= 'a' && r <= 'z') || (r >= 'A' && r <= 'Z') || (r >= '0' && r <= '9') || r == '_' || r == '@' || r == '.' || r == '-' {
+			result.WriteRune(r)
+		}
+	}
+	return strings.TrimSpace(result.String())
+}

internal/cmd/iflow_cookie.go

@@ -71,22 +71,9 @@ func promptForCookie(promptFn func(string) (string, error)) (string, error) {
 		return "", fmt.Errorf("failed to read cookie: %w", err)
 	}
 
-	line = strings.TrimSpace(line)
-	if line == "" {
-		return "", fmt.Errorf("cookie cannot be empty")
-	}
-
-	// Clean up any extra whitespace and join multiple spaces
-	cookie := strings.Join(strings.Fields(line), " ")
-
-	// Ensure it ends properly
-	if !strings.HasSuffix(cookie, ";") {
-		cookie = cookie + ";"
-	}
-
-	// Ensure BXAuth is present in the cookie
-	if !strings.Contains(cookie, "BXAuth=") {
-		return "", fmt.Errorf("BXAuth field not found in cookie")
+	cookie, err := iflow.NormalizeCookie(line)
+	if err != nil {
+		return "", err
 	}
 
 	return cookie, nil
@@ -94,17 +81,6 @@ func promptForCookie(promptFn func(string) (string, error)) (string, error) {
 
 // getAuthFilePath returns the auth file path for the given provider and email
 func getAuthFilePath(cfg *config.Config, provider, email string) string {
-	// Clean email to make it filename-safe
-	cleanEmail := strings.ReplaceAll(email, "*", "x")
-
-	// Remove any unsafe characters, but allow standard email chars (@, ., -)
-	var result strings.Builder
-	for _, r := range cleanEmail {
-		if (r >= 'a' && r <= 'z') || (r >= 'A' && r <= 'Z') || (r >= '0' && r <= '9') ||
-			r == '_' || r == '@' || r == '.' || r == '-' {
-			result.WriteRune(r)
-		}
-	}
-
-	return fmt.Sprintf("%s/%s-%s.json", cfg.AuthDir, provider, result.String())
+	fileName := iflow.SanitizeIFlowFileName(email)
+	return fmt.Sprintf("%s/%s-%s.json", cfg.AuthDir, provider, fileName)
 }

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",
@@ -116,34 +116,110 @@ func GeminiModels() []*ModelInfo {
 			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},
+		},
 	}
 }
 
-// GetGeminiModels returns the standard Gemini model definitions
-func GetGeminiModels() []*ModelInfo { return GeminiModels() }
+func GetGeminiVertexModels() []*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",
+			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-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",
@@ -155,10 +231,25 @@ 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",
@@ -170,122 +261,163 @@ func GetGeminiCLIModels() []*ModelInfo {
 			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
 			Thinking:                   &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true},
 		},
-		// {
-		// 	ID:                         "gemini-3-pro-preview-11-2025",
-		// 	Object:                     "model",
-		// 	Created:                    time.Now().Unix(),
-		// 	OwnedBy:                    "google",
-		// 	Type:                       "gemini",
-		// 	Name:                       "models/gemini-3-pro-preview-11-2025",
-		// 	Version:                    "3",
-		// 	DisplayName:                "Gemini 3 Pro Preview 11-2025",
-		// 	Description:                "Latest preview 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-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},
+		},
 	}
 }
 
 // GetAIStudioModels returns the Gemini model definitions for AI Studio integrations
 func GetAIStudioModels() []*ModelInfo {
-	base := GeminiModels()
-
-	return append(base,
-		[]*ModelInfo{
-			{
-				ID:                         "gemini-3-pro-preview",
-				Object:                     "model",
-				Created:                    time.Now().Unix(),
-				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:                    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

internal/runtime/executor/gemini_cli_executor.go

@@ -180,7 +180,7 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
 			continue
 		}
 
-		err = statusErr{code: httpResp.StatusCode, msg: string(data)}
+		err = newGeminiStatusErr(httpResp.StatusCode, data)
 		return resp, err
 	}
 
@@ -190,7 +190,7 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
 	if lastStatus == 0 {
 		lastStatus = 429
 	}
-	err = statusErr{code: lastStatus, msg: string(lastBody)}
+	err = newGeminiStatusErr(lastStatus, lastBody)
 	return resp, err
 }
 
@@ -304,7 +304,7 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 				}
 				continue
 			}
-			err = statusErr{code: httpResp.StatusCode, msg: string(data)}
+			err = newGeminiStatusErr(httpResp.StatusCode, data)
 			return nil, err
 		}
 
@@ -377,7 +377,7 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 	if lastStatus == 0 {
 		lastStatus = 429
 	}
-	err = statusErr{code: lastStatus, msg: string(lastBody)}
+	err = newGeminiStatusErr(lastStatus, lastBody)
 	return nil, err
 }
 
@@ -485,7 +485,7 @@ func (e *GeminiCLIExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.
 	if lastStatus == 0 {
 		lastStatus = 429
 	}
-	return cliproxyexecutor.Response{}, statusErr{code: lastStatus, msg: string(lastBody)}
+	return cliproxyexecutor.Response{}, newGeminiStatusErr(lastStatus, lastBody)
 }
 
 func (e *GeminiCLIExecutor) Refresh(ctx context.Context, auth *cliproxyauth.Auth) (*cliproxyauth.Auth, error) {
@@ -769,3 +769,42 @@ func fixGeminiCLIImageAspectRatio(modelName string, rawJSON []byte) []byte {
 	}
 	return rawJSON
 }
+
+func newGeminiStatusErr(statusCode int, body []byte) statusErr {
+	err := statusErr{code: statusCode, msg: string(body)}
+	if statusCode == http.StatusTooManyRequests {
+		if retryAfter, parseErr := parseRetryDelay(body); parseErr == nil && retryAfter != nil {
+			err.retryAfter = retryAfter
+		}
+	}
+	return err
+}
+
+// parseRetryDelay extracts the retry delay from a Google API 429 error response.
+// The error response contains a RetryInfo.retryDelay field in the format "0.847655010s".
+// Returns the parsed duration or an error if it cannot be determined.
+func parseRetryDelay(errorBody []byte) (*time.Duration, error) {
+	// Try to parse the retryDelay from the error response
+	// Format: error.details[].retryDelay where @type == "type.googleapis.com/google.rpc.RetryInfo"
+	details := gjson.GetBytes(errorBody, "error.details")
+	if !details.Exists() || !details.IsArray() {
+		return nil, fmt.Errorf("no error.details found")
+	}
+
+	for _, detail := range details.Array() {
+		typeVal := detail.Get("@type").String()
+		if typeVal == "type.googleapis.com/google.rpc.RetryInfo" {
+			retryDelay := detail.Get("retryDelay").String()
+			if retryDelay != "" {
+				// Parse duration string like "0.847655010s"
+				duration, err := time.ParseDuration(retryDelay)
+				if err != nil {
+					return nil, fmt.Errorf("failed to parse duration")
+				}
+				return &duration, nil
+			}
+		}
+	}
+
+	return nil, fmt.Errorf("no RetryInfo found")
+}

internal/runtime/executor/openai_compat_executor.go

@@ -8,6 +8,7 @@ import (
 	"io"
 	"net/http"
 	"strings"
+	"time"
 
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
@@ -340,8 +341,9 @@ func (e *OpenAICompatExecutor) overrideModel(payload []byte, model string) []byt
 }
 
 type statusErr struct {
-	code int
-	msg  string
+	code       int
+	msg        string
+	retryAfter *time.Duration
 }
 
 func (e statusErr) Error() string {
@@ -350,4 +352,5 @@ func (e statusErr) Error() string {
 	}
 	return fmt.Sprintf("status %d", e.code)
 }
-func (e statusErr) StatusCode() int { return e.code }
+func (e statusErr) StatusCode() int            { return e.code }
+func (e statusErr) RetryAfter() *time.Duration { return e.retryAfter }

internal/translator/codex/openai/responses/codex_openai-responses_request.go

@@ -22,6 +22,7 @@ func ConvertOpenAIResponsesRequestToCodex(modelName string, inputRawJSON []byte,
 	rawJSON, _ = sjson.DeleteBytes(rawJSON, "max_completion_tokens")
 	rawJSON, _ = sjson.DeleteBytes(rawJSON, "temperature")
 	rawJSON, _ = sjson.DeleteBytes(rawJSON, "top_p")
+	rawJSON, _ = sjson.DeleteBytes(rawJSON, "service_tier")
 
 	originalInstructions := ""
 	originalInstructionsText := ""

internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go

@@ -88,6 +88,15 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 		}
 	}
 
+	// For gemini-3-pro-preview, always send default thinkingConfig when none specified.
+	// This matches the official Gemini CLI behavior which always sends:
+	// { thinkingBudget: -1, includeThoughts: true }
+	// See: ai-gemini-cli/packages/core/src/config/defaultModelConfigs.ts
+	if !gjson.GetBytes(out, "request.generationConfig.thinkingConfig").Exists() && modelName == "gemini-3-pro-preview" {
+		out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
+		out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
+	}
+
 	// Temperature/top_p/top_k
 	if tr := gjson.GetBytes(rawJSON, "temperature"); tr.Exists() && tr.Type == gjson.Number {
 		out, _ = sjson.SetBytes(out, "request.generationConfig.temperature", tr.Num)

internal/translator/gemini/openai/responses/gemini_openai-responses_request.go

@@ -6,6 +6,7 @@ import (
 
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/translator/gemini/common"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
+	log "github.com/sirupsen/logrus"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -294,6 +295,17 @@ func ConvertOpenAIResponsesRequestToGemini(modelName string, inputRawJSON []byte
 			}
 		}
 	}
+
+	// For gemini-3-pro-preview, always send default thinkingConfig when none specified.
+	// This matches the official Gemini CLI behavior which always sends:
+	// { thinkingBudget: -1, includeThoughts: true }
+	// See: ai-gemini-cli/packages/core/src/config/defaultModelConfigs.ts
+	if !gjson.Get(out, "generationConfig.thinkingConfig").Exists() && modelName == "gemini-3-pro-preview" {
+		out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
+		out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)
+		log.Debugf("Applied default thinkingConfig for gemini-3-pro-preview (matches Gemini CLI): thinkingBudget=-1, include_thoughts=true")
+	}
+
 	result := []byte(out)
 	result = common.AttachDefaultSafetySettings(result, "safetySettings")
 	return result

sdk/cliproxy/auth/manager.go

@@ -62,6 +62,8 @@ type Result struct {
 	Model string
 	// Success marks whether the execution succeeded.
 	Success bool
+	// RetryAfter carries a provider supplied retry hint (e.g. 429 retryDelay).
+	RetryAfter *time.Duration
 	// Error describes the failure when Success is false.
 	Error *Error
 }
@@ -325,6 +327,9 @@ func (m *Manager) executeWithProvider(ctx context.Context, provider string, req
 			if errors.As(errExec, &se) && se != nil {
 				result.Error.HTTPStatus = se.StatusCode()
 			}
+			if ra := retryAfterFromError(errExec); ra != nil {
+				result.RetryAfter = ra
+			}
 			m.MarkResult(execCtx, result)
 			lastErr = errExec
 			continue
@@ -370,6 +375,9 @@ func (m *Manager) executeCountWithProvider(ctx context.Context, provider string,
 			if errors.As(errExec, &se) && se != nil {
 				result.Error.HTTPStatus = se.StatusCode()
 			}
+			if ra := retryAfterFromError(errExec); ra != nil {
+				result.RetryAfter = ra
+			}
 			m.MarkResult(execCtx, result)
 			lastErr = errExec
 			continue
@@ -415,6 +423,7 @@ func (m *Manager) executeStreamWithProvider(ctx context.Context, provider string
 				rerr.HTTPStatus = se.StatusCode()
 			}
 			result := Result{AuthID: auth.ID, Provider: provider, Model: req.Model, Success: false, Error: rerr}
+			result.RetryAfter = retryAfterFromError(errStream)
 			m.MarkResult(execCtx, result)
 			lastErr = errStream
 			continue
@@ -556,17 +565,23 @@ func (m *Manager) MarkResult(ctx context.Context, result Result) {
 					suspendReason = "payment_required"
 					shouldSuspendModel = true
 				case 429:
-					cooldown, nextLevel := nextQuotaCooldown(state.Quota.BackoffLevel)
 					var next time.Time
-					if cooldown > 0 {
-						next = now.Add(cooldown)
+					backoffLevel := state.Quota.BackoffLevel
+					if result.RetryAfter != nil {
+						next = now.Add(*result.RetryAfter)
+					} else {
+						cooldown, nextLevel := nextQuotaCooldown(backoffLevel)
+						if cooldown > 0 {
+							next = now.Add(cooldown)
+						}
+						backoffLevel = nextLevel
 					}
 					state.NextRetryAfter = next
 					state.Quota = QuotaState{
 						Exceeded:      true,
 						Reason:        "quota",
 						NextRecoverAt: next,
-						BackoffLevel:  nextLevel,
+						BackoffLevel:  backoffLevel,
 					}
 					suspendReason = "quota"
 					shouldSuspendModel = true
@@ -582,7 +597,7 @@ func (m *Manager) MarkResult(ctx context.Context, result Result) {
 				auth.UpdatedAt = now
 				updateAggregatedAvailability(auth, now)
 			} else {
-				applyAuthFailureState(auth, result.Error, now)
+				applyAuthFailureState(auth, result.Error, result.RetryAfter, now)
 			}
 		}
 
@@ -742,6 +757,25 @@ func cloneError(err *Error) *Error {
 	}
 }
 
+func retryAfterFromError(err error) *time.Duration {
+	if err == nil {
+		return nil
+	}
+	type retryAfterProvider interface {
+		RetryAfter() *time.Duration
+	}
+	rap, ok := err.(retryAfterProvider)
+	if !ok || rap == nil {
+		return nil
+	}
+	retryAfter := rap.RetryAfter()
+	if retryAfter == nil {
+		return nil
+	}
+	val := *retryAfter
+	return &val
+}
+
 func statusCodeFromResult(err *Error) int {
 	if err == nil {
 		return 0
@@ -749,7 +783,7 @@ func statusCodeFromResult(err *Error) int {
 	return err.StatusCode()
 }
 
-func applyAuthFailureState(auth *Auth, resultErr *Error, now time.Time) {
+func applyAuthFailureState(auth *Auth, resultErr *Error, retryAfter *time.Duration, now time.Time) {
 	if auth == nil {
 		return
 	}
@@ -774,13 +808,17 @@ func applyAuthFailureState(auth *Auth, resultErr *Error, now time.Time) {
 		auth.StatusMessage = "quota exhausted"
 		auth.Quota.Exceeded = true
 		auth.Quota.Reason = "quota"
-		cooldown, nextLevel := nextQuotaCooldown(auth.Quota.BackoffLevel)
 		var next time.Time
-		if cooldown > 0 {
-			next = now.Add(cooldown)
+		if retryAfter != nil {
+			next = now.Add(*retryAfter)
+		} else {
+			cooldown, nextLevel := nextQuotaCooldown(auth.Quota.BackoffLevel)
+			if cooldown > 0 {
+				next = now.Add(cooldown)
+			}
+			auth.Quota.BackoffLevel = nextLevel
 		}
 		auth.Quota.NextRecoverAt = next
-		auth.Quota.BackoffLevel = nextLevel
 		auth.NextRetryAfter = next
 	case 408, 500, 502, 503, 504:
 		auth.StatusMessage = "transient upstream error"

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":