diff --git a/backend/internal/pkg/openai/constants.go b/backend/internal/pkg/openai/constants.go
index 49e38bf8..980f058d 100644
--- a/backend/internal/pkg/openai/constants.go
+++ b/backend/internal/pkg/openai/constants.go
@@ -17,16 +17,9 @@ type Model struct {
 var DefaultModels = []Model{
 	{ID: "gpt-5.4", Object: "model", Created: 1738368000, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.4"},
 	{ID: "gpt-5.4-mini", Object: "model", Created: 1738368000, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.4 Mini"},
-	{ID: "gpt-5.4-nano", Object: "model", Created: 1738368000, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.4 Nano"},
 	{ID: "gpt-5.3-codex", Object: "model", Created: 1735689600, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.3 Codex"},
 	{ID: "gpt-5.3-codex-spark", Object: "model", Created: 1735689600, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.3 Codex Spark"},
 	{ID: "gpt-5.2", Object: "model", Created: 1733875200, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.2"},
-	{ID: "gpt-5.2-codex", Object: "model", Created: 1733011200, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.2 Codex"},
-	{ID: "gpt-5.1-codex-max", Object: "model", Created: 1730419200, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.1 Codex Max"},
-	{ID: "gpt-5.1-codex", Object: "model", Created: 1730419200, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.1 Codex"},
-	{ID: "gpt-5.1", Object: "model", Created: 1731456000, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.1"},
-	{ID: "gpt-5.1-codex-mini", Object: "model", Created: 1730419200, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5.1 Codex Mini"},
-	{ID: "gpt-5", Object: "model", Created: 1722988800, OwnedBy: "openai", Type: "model", DisplayName: "GPT-5"},
 }
 
 // DefaultModelIDs returns the default model ID list
@@ -39,7 +32,7 @@ func DefaultModelIDs() []string {
 }
 
 // DefaultTestModel default model for testing OpenAI accounts
-const DefaultTestModel = "gpt-5.1-codex"
+const DefaultTestModel = "gpt-5.4"
 
 // DefaultInstructions default instructions for non-Codex CLI requests
 // Content loaded from instructions.txt at compile time
diff --git a/backend/internal/service/billing_service.go b/backend/internal/service/billing_service.go
index c9f32b3b..a45203a3 100644
--- a/backend/internal/service/billing_service.go
+++ b/backend/internal/service/billing_service.go
@@ -203,17 +203,6 @@ func (s *BillingService) initFallbackPricing() {
 		SupportsCacheBreakdown:     false,
 	}
 
-	// OpenAI GPT-5.1（本地兜底，防止动态定价不可用时拒绝计费）
-	s.fallbackPrices["gpt-5.1"] = &ModelPricing{
-		InputPricePerToken:             1.25e-6, // $1.25 per MTok
-		InputPricePerTokenPriority:     2.5e-6,  // $2.5 per MTok
-		OutputPricePerToken:            10e-6,   // $10 per MTok
-		OutputPricePerTokenPriority:    20e-6,   // $20 per MTok
-		CacheCreationPricePerToken:     1.25e-6, // $1.25 per MTok
-		CacheReadPricePerToken:         0.125e-6,
-		CacheReadPricePerTokenPriority: 0.25e-6,
-		SupportsCacheBreakdown:         false,
-	}
 	// OpenAI GPT-5.4（业务指定价格）
 	s.fallbackPrices["gpt-5.4"] = &ModelPricing{
 		InputPricePerToken:             2.5e-6,  // $2.5 per MTok
@@ -234,12 +223,6 @@ func (s *BillingService) initFallbackPricing() {
 		CacheReadPricePerToken: 7.5e-8,
 		SupportsCacheBreakdown: false,
 	}
-	s.fallbackPrices["gpt-5.4-nano"] = &ModelPricing{
-		InputPricePerToken:     2e-7,
-		OutputPricePerToken:    1.25e-6,
-		CacheReadPricePerToken: 2e-8,
-		SupportsCacheBreakdown: false,
-	}
 	// OpenAI GPT-5.2（本地兜底）
 	s.fallbackPrices["gpt-5.2"] = &ModelPricing{
 		InputPricePerToken:             1.75e-6,
@@ -251,8 +234,8 @@ func (s *BillingService) initFallbackPricing() {
 		CacheReadPricePerTokenPriority: 0.35e-6,
 		SupportsCacheBreakdown:         false,
 	}
-	// Codex 族兜底统一按 GPT-5.1 Codex 价格计费
-	s.fallbackPrices["gpt-5.1-codex"] = &ModelPricing{
+	// Codex 族兜底统一按 GPT-5.3 Codex 价格计费
+	s.fallbackPrices["gpt-5.3-codex"] = &ModelPricing{
 		InputPricePerToken:             1.5e-6, // $1.5 per MTok
 		InputPricePerTokenPriority:     3e-6,   // $3 per MTok
 		OutputPricePerToken:            12e-6,  // $12 per MTok
@@ -262,17 +245,6 @@ func (s *BillingService) initFallbackPricing() {
 		CacheReadPricePerTokenPriority: 0.3e-6,
 		SupportsCacheBreakdown:         false,
 	}
-	s.fallbackPrices["gpt-5.2-codex"] = &ModelPricing{
-		InputPricePerToken:             1.75e-6,
-		InputPricePerTokenPriority:     3.5e-6,
-		OutputPricePerToken:            14e-6,
-		OutputPricePerTokenPriority:    28e-6,
-		CacheCreationPricePerToken:     1.75e-6,
-		CacheReadPricePerToken:         0.175e-6,
-		CacheReadPricePerTokenPriority: 0.35e-6,
-		SupportsCacheBreakdown:         false,
-	}
-	s.fallbackPrices["gpt-5.3-codex"] = s.fallbackPrices["gpt-5.1-codex"]
 }
 
 // getFallbackPricing 根据模型系列获取回退价格
@@ -318,20 +290,12 @@ func (s *BillingService) getFallbackPricing(model string) *ModelPricing {
 		switch normalized {
 		case "gpt-5.4-mini":
 			return s.fallbackPrices["gpt-5.4-mini"]
-		case "gpt-5.4-nano":
-			return s.fallbackPrices["gpt-5.4-nano"]
 		case "gpt-5.4":
 			return s.fallbackPrices["gpt-5.4"]
 		case "gpt-5.2":
 			return s.fallbackPrices["gpt-5.2"]
-		case "gpt-5.2-codex":
-			return s.fallbackPrices["gpt-5.2-codex"]
-		case "gpt-5.3-codex":
+		case "gpt-5.3-codex", "gpt-5.3-codex-spark":
 			return s.fallbackPrices["gpt-5.3-codex"]
-		case "gpt-5.1-codex", "gpt-5.1-codex-max", "gpt-5.1-codex-mini", "codex-mini-latest":
-			return s.fallbackPrices["gpt-5.1-codex"]
-		case "gpt-5.1":
-			return s.fallbackPrices["gpt-5.1"]
 		}
 	}
 
@@ -667,8 +631,13 @@ func (s *BillingService) shouldApplySessionLongContextPricing(tokens UsageTokens
 }
 
 func isOpenAIGPT54Model(model string) bool {
-	normalized := normalizeCodexModel(strings.TrimSpace(strings.ToLower(model)))
-	return normalized == "gpt-5.4"
+	trimmed := strings.TrimSpace(strings.ToLower(model))
+	// 仅当模型字符串实际属于 GPT-5/Codex 族时才做归一判定，避免 normalizeCodexModel
+	// 的默认兜底把非 OpenAI 模型（claude-*、gemini-*、gpt-4o）误识别为 gpt-5.4。
+	if !strings.Contains(trimmed, "gpt-5") && !strings.Contains(trimmed, "codex") {
+		return false
+	}
+	return normalizeCodexModel(trimmed) == "gpt-5.4"
 }
 
 // CalculateCostWithConfig 使用配置中的默认倍率计算费用
diff --git a/backend/internal/service/billing_service_test.go b/backend/internal/service/billing_service_test.go
index fc8361c7..222abd69 100644
--- a/backend/internal/service/billing_service_test.go
+++ b/backend/internal/service/billing_service_test.go
@@ -123,15 +123,6 @@ func TestGetModelPricing_UnknownOpenAIModelReturnsError(t *testing.T) {
 	require.Contains(t, err.Error(), "pricing not found")
 }
 
-func TestGetModelPricing_OpenAIGPT51Fallback(t *testing.T) {
-	svc := newTestBillingService()
-
-	pricing, err := svc.GetModelPricing("gpt-5.1")
-	require.NoError(t, err)
-	require.NotNil(t, pricing)
-	require.InDelta(t, 1.25e-6, pricing.InputPricePerToken, 1e-12)
-}
-
 func TestGetModelPricing_OpenAIGPT54Fallback(t *testing.T) {
 	svc := newTestBillingService()
 
@@ -158,18 +149,6 @@ func TestGetModelPricing_OpenAIGPT54MiniFallback(t *testing.T) {
 	require.Zero(t, pricing.LongContextInputThreshold)
 }
 
-func TestGetModelPricing_OpenAIGPT54NanoFallback(t *testing.T) {
-	svc := newTestBillingService()
-
-	pricing, err := svc.GetModelPricing("gpt-5.4-nano")
-	require.NoError(t, err)
-	require.NotNil(t, pricing)
-	require.InDelta(t, 2e-7, pricing.InputPricePerToken, 1e-12)
-	require.InDelta(t, 1.25e-6, pricing.OutputPricePerToken, 1e-12)
-	require.InDelta(t, 2e-8, pricing.CacheReadPricePerToken, 1e-12)
-	require.Zero(t, pricing.LongContextInputThreshold)
-}
-
 func TestCalculateCost_OpenAIGPT54LongContextAppliesWholeSessionMultipliers(t *testing.T) {
 	svc := newTestBillingService()
 
@@ -204,13 +183,13 @@ func TestGetFallbackPricing_FamilyMatching(t *testing.T) {
 		{name: "claude generic model fallback sonnet", model: "claude-foo-bar", expectedInput: 3e-6},
 		{name: "gemini explicit fallback", model: "gemini-3-1-pro", expectedInput: 2e-6},
 		{name: "gemini unknown no fallback", model: "gemini-2.0-pro", expectNilPricing: true},
-		{name: "openai gpt5.1", model: "gpt-5.1", expectedInput: 1.25e-6},
 		{name: "openai gpt5.4", model: "gpt-5.4", expectedInput: 2.5e-6},
 		{name: "openai gpt5.4 mini", model: "gpt-5.4-mini", expectedInput: 7.5e-7},
-		{name: "openai gpt5.4 nano", model: "gpt-5.4-nano", expectedInput: 2e-7},
 		{name: "openai gpt5.3 codex", model: "gpt-5.3-codex", expectedInput: 1.5e-6},
-		{name: "openai gpt5.1 codex max alias", model: "gpt-5.1-codex-max", expectedInput: 1.5e-6},
-		{name: "openai codex mini latest alias", model: "codex-mini-latest", expectedInput: 1.5e-6},
+		{name: "openai gpt5.3 codex spark", model: "gpt-5.3-codex-spark", expectedInput: 1.5e-6},
+		{name: "openai legacy gpt5.1 falls back to gpt5.4", model: "gpt-5.1", expectedInput: 2.5e-6},
+		{name: "openai legacy gpt5.1 codex falls back to gpt5.3 codex", model: "gpt-5.1-codex", expectedInput: 1.5e-6},
+		{name: "openai legacy codex mini latest falls back to gpt5.3 codex", model: "codex-mini-latest", expectedInput: 1.5e-6},
 		{name: "openai unknown no fallback", model: "gpt-unknown-model", expectNilPricing: true},
 		{name: "non supported family", model: "qwen-max", expectNilPricing: true},
 	}
diff --git a/backend/internal/service/openai_codex_transform.go b/backend/internal/service/openai_codex_transform.go
index a266d6a0..457309d3 100644
--- a/backend/internal/service/openai_codex_transform.go
+++ b/backend/internal/service/openai_codex_transform.go
@@ -8,7 +8,6 @@ import (
 var codexModelMap = map[string]string{
 	"gpt-5.4":                    "gpt-5.4",
 	"gpt-5.4-mini":               "gpt-5.4-mini",
-	"gpt-5.4-nano":               "gpt-5.4-nano",
 	"gpt-5.4-none":               "gpt-5.4",
 	"gpt-5.4-low":                "gpt-5.4",
 	"gpt-5.4-medium":             "gpt-5.4",
@@ -22,52 +21,21 @@ var codexModelMap = map[string]string{
 	"gpt-5.3-high":               "gpt-5.3-codex",
 	"gpt-5.3-xhigh":              "gpt-5.3-codex",
 	"gpt-5.3-codex":              "gpt-5.3-codex",
-	"gpt-5.3-codex-spark":        "gpt-5.3-codex",
-	"gpt-5.3-codex-spark-low":    "gpt-5.3-codex",
-	"gpt-5.3-codex-spark-medium": "gpt-5.3-codex",
-	"gpt-5.3-codex-spark-high":   "gpt-5.3-codex",
-	"gpt-5.3-codex-spark-xhigh":  "gpt-5.3-codex",
+	"gpt-5.3-codex-spark":        "gpt-5.3-codex-spark",
+	"gpt-5.3-codex-spark-low":    "gpt-5.3-codex-spark",
+	"gpt-5.3-codex-spark-medium": "gpt-5.3-codex-spark",
+	"gpt-5.3-codex-spark-high":   "gpt-5.3-codex-spark",
+	"gpt-5.3-codex-spark-xhigh":  "gpt-5.3-codex-spark",
 	"gpt-5.3-codex-low":          "gpt-5.3-codex",
 	"gpt-5.3-codex-medium":       "gpt-5.3-codex",
 	"gpt-5.3-codex-high":         "gpt-5.3-codex",
 	"gpt-5.3-codex-xhigh":        "gpt-5.3-codex",
-	"gpt-5.1-codex":              "gpt-5.1-codex",
-	"gpt-5.1-codex-low":          "gpt-5.1-codex",
-	"gpt-5.1-codex-medium":       "gpt-5.1-codex",
-	"gpt-5.1-codex-high":         "gpt-5.1-codex",
-	"gpt-5.1-codex-max":          "gpt-5.1-codex-max",
-	"gpt-5.1-codex-max-low":      "gpt-5.1-codex-max",
-	"gpt-5.1-codex-max-medium":   "gpt-5.1-codex-max",
-	"gpt-5.1-codex-max-high":     "gpt-5.1-codex-max",
-	"gpt-5.1-codex-max-xhigh":    "gpt-5.1-codex-max",
 	"gpt-5.2":                    "gpt-5.2",
 	"gpt-5.2-none":               "gpt-5.2",
 	"gpt-5.2-low":                "gpt-5.2",
 	"gpt-5.2-medium":             "gpt-5.2",
 	"gpt-5.2-high":               "gpt-5.2",
 	"gpt-5.2-xhigh":              "gpt-5.2",
-	"gpt-5.2-codex":              "gpt-5.2-codex",
-	"gpt-5.2-codex-low":          "gpt-5.2-codex",
-	"gpt-5.2-codex-medium":       "gpt-5.2-codex",
-	"gpt-5.2-codex-high":         "gpt-5.2-codex",
-	"gpt-5.2-codex-xhigh":        "gpt-5.2-codex",
-	"gpt-5.1-codex-mini":         "gpt-5.1-codex-mini",
-	"gpt-5.1-codex-mini-medium":  "gpt-5.1-codex-mini",
-	"gpt-5.1-codex-mini-high":    "gpt-5.1-codex-mini",
-	"gpt-5.1":                    "gpt-5.1",
-	"gpt-5.1-none":               "gpt-5.1",
-	"gpt-5.1-low":                "gpt-5.1",
-	"gpt-5.1-medium":             "gpt-5.1",
-	"gpt-5.1-high":               "gpt-5.1",
-	"gpt-5.1-chat-latest":        "gpt-5.1",
-	"gpt-5-codex":                "gpt-5.1-codex",
-	"codex-mini-latest":          "gpt-5.1-codex-mini",
-	"gpt-5-codex-mini":           "gpt-5.1-codex-mini",
-	"gpt-5-codex-mini-medium":    "gpt-5.1-codex-mini",
-	"gpt-5-codex-mini-high":      "gpt-5.1-codex-mini",
-	"gpt-5":                      "gpt-5.1",
-	"gpt-5-mini":                 "gpt-5.1",
-	"gpt-5-nano":                 "gpt-5.1",
 }
 
 type codexTransformResult struct {
@@ -220,7 +188,7 @@ func applyCodexOAuthTransform(reqBody map[string]any, isCodexCLI bool, isCompact
 
 func normalizeCodexModel(model string) string {
 	if model == "" {
-		return "gpt-5.1"
+		return "gpt-5.4"
 	}
 
 	modelID := model
@@ -238,49 +206,29 @@ func normalizeCodexModel(model string) string {
 	if strings.Contains(normalized, "gpt-5.4-mini") || strings.Contains(normalized, "gpt 5.4 mini") {
 		return "gpt-5.4-mini"
 	}
-	if strings.Contains(normalized, "gpt-5.4-nano") || strings.Contains(normalized, "gpt 5.4 nano") {
-		return "gpt-5.4-nano"
-	}
 	if strings.Contains(normalized, "gpt-5.4") || strings.Contains(normalized, "gpt 5.4") {
 		return "gpt-5.4"
 	}
-	if strings.Contains(normalized, "gpt-5.2-codex") || strings.Contains(normalized, "gpt 5.2 codex") {
-		return "gpt-5.2-codex"
-	}
 	if strings.Contains(normalized, "gpt-5.2") || strings.Contains(normalized, "gpt 5.2") {
 		return "gpt-5.2"
 	}
+	if strings.Contains(normalized, "gpt-5.3-codex-spark") || strings.Contains(normalized, "gpt 5.3 codex spark") {
+		return "gpt-5.3-codex-spark"
+	}
 	if strings.Contains(normalized, "gpt-5.3-codex") || strings.Contains(normalized, "gpt 5.3 codex") {
 		return "gpt-5.3-codex"
 	}
 	if strings.Contains(normalized, "gpt-5.3") || strings.Contains(normalized, "gpt 5.3") {
 		return "gpt-5.3-codex"
 	}
-	if strings.Contains(normalized, "gpt-5.1-codex-max") || strings.Contains(normalized, "gpt 5.1 codex max") {
-		return "gpt-5.1-codex-max"
-	}
-	if strings.Contains(normalized, "gpt-5.1-codex-mini") || strings.Contains(normalized, "gpt 5.1 codex mini") {
-		return "gpt-5.1-codex-mini"
-	}
-	if strings.Contains(normalized, "codex-mini-latest") ||
-		strings.Contains(normalized, "gpt-5-codex-mini") ||
-		strings.Contains(normalized, "gpt 5 codex mini") {
-		return "codex-mini-latest"
-	}
-	if strings.Contains(normalized, "gpt-5.1-codex") || strings.Contains(normalized, "gpt 5.1 codex") {
-		return "gpt-5.1-codex"
-	}
-	if strings.Contains(normalized, "gpt-5.1") || strings.Contains(normalized, "gpt 5.1") {
-		return "gpt-5.1"
-	}
 	if strings.Contains(normalized, "codex") {
-		return "gpt-5.1-codex"
+		return "gpt-5.3-codex"
 	}
 	if strings.Contains(normalized, "gpt-5") || strings.Contains(normalized, "gpt 5") {
-		return "gpt-5.1"
+		return "gpt-5.4"
 	}
 
-	return "gpt-5.1"
+	return "gpt-5.4"
 }
 
 func normalizeOpenAIModelForUpstream(account *Account, model string) string {
diff --git a/backend/internal/service/openai_codex_transform_test.go b/backend/internal/service/openai_codex_transform_test.go
index 993ade07..22264f5e 100644
--- a/backend/internal/service/openai_codex_transform_test.go
+++ b/backend/internal/service/openai_codex_transform_test.go
@@ -240,15 +240,13 @@ func TestNormalizeCodexModel_Gpt53(t *testing.T) {
 		"gpt 5.4":                   "gpt-5.4",
 		"gpt-5.4-mini":              "gpt-5.4-mini",
 		"gpt 5.4 mini":              "gpt-5.4-mini",
-		"gpt-5.4-nano":              "gpt-5.4-nano",
-		"gpt 5.4 nano":              "gpt-5.4-nano",
 		"gpt-5.3":                   "gpt-5.3-codex",
 		"gpt-5.3-codex":             "gpt-5.3-codex",
 		"gpt-5.3-codex-xhigh":       "gpt-5.3-codex",
-		"gpt-5.3-codex-spark":       "gpt-5.3-codex",
-		"gpt 5.3 codex spark":       "gpt-5.3-codex",
-		"gpt-5.3-codex-spark-high":  "gpt-5.3-codex",
-		"gpt-5.3-codex-spark-xhigh": "gpt-5.3-codex",
+		"gpt-5.3-codex-spark":       "gpt-5.3-codex-spark",
+		"gpt 5.3 codex spark":       "gpt-5.3-codex-spark",
+		"gpt-5.3-codex-spark-high":  "gpt-5.3-codex-spark",
+		"gpt-5.3-codex-spark-xhigh": "gpt-5.3-codex-spark",
 		"gpt 5.3 codex":             "gpt-5.3-codex",
 	}
 
@@ -257,6 +255,26 @@ func TestNormalizeCodexModel_Gpt53(t *testing.T) {
 	}
 }
 
+func TestNormalizeCodexModel_RemovedModelsFallbackToSupportedTargets(t *testing.T) {
+	cases := map[string]string{
+		"":                   "gpt-5.4",
+		"gpt-5":              "gpt-5.4",
+		"gpt-5-mini":         "gpt-5.4",
+		"gpt-5-nano":         "gpt-5.4",
+		"gpt-5.1":            "gpt-5.4",
+		"gpt-5.1-codex":      "gpt-5.3-codex",
+		"gpt-5.1-codex-max":  "gpt-5.3-codex",
+		"gpt-5.1-codex-mini": "gpt-5.3-codex",
+		"gpt-5.2-codex":      "gpt-5.2",
+		"codex-mini-latest":  "gpt-5.3-codex",
+		"gpt-5-codex":        "gpt-5.3-codex",
+	}
+
+	for input, expected := range cases {
+		require.Equal(t, expected, normalizeCodexModel(input))
+	}
+}
+
 func TestApplyCodexOAuthTransform_PreservesBareSparkModel(t *testing.T) {
 	reqBody := map[string]any{
 		"model": "gpt-5.3-codex-spark",
diff --git a/backend/internal/service/openai_compat_prompt_cache_key.go b/backend/internal/service/openai_compat_prompt_cache_key.go
index 88e16a4d..fcd27f19 100644
--- a/backend/internal/service/openai_compat_prompt_cache_key.go
+++ b/backend/internal/service/openai_compat_prompt_cache_key.go
@@ -10,8 +10,14 @@ import (
 const compatPromptCacheKeyPrefix = "compat_cc_"
 
 func shouldAutoInjectPromptCacheKeyForCompat(model string) bool {
-	switch normalizeCodexModel(strings.TrimSpace(model)) {
-	case "gpt-5.4", "gpt-5.3-codex":
+	trimmed := strings.TrimSpace(strings.ToLower(model))
+	// 仅对 Codex OAuth 路径支持的 GPT-5 族开启自动注入，避免 normalizeCodexModel
+	// 的默认兜底把任意模型（如 gpt-4o、claude-*）误判为 gpt-5.4。
+	if !strings.Contains(trimmed, "gpt-5") && !strings.Contains(trimmed, "codex") {
+		return false
+	}
+	switch normalizeCodexModel(trimmed) {
+	case "gpt-5.4", "gpt-5.3-codex", "gpt-5.3-codex-spark":
 		return true
 	default:
 		return false
diff --git a/backend/internal/service/openai_model_mapping_test.go b/backend/internal/service/openai_model_mapping_test.go
index cda7e369..35e7c250 100644
--- a/backend/internal/service/openai_model_mapping_test.go
+++ b/backend/internal/service/openai_model_mapping_test.go
@@ -69,14 +69,14 @@ func TestResolveOpenAIForwardModel(t *testing.T) {
 	}
 }
 
-func TestResolveOpenAIForwardModel_PreventsClaudeModelFromFallingBackToGpt51(t *testing.T) {
+func TestResolveOpenAIForwardModel_PreventsClaudeModelFromFallingBackToGpt54(t *testing.T) {
 	account := &Account{
 		Credentials: map[string]any{},
 	}
 
 	withoutDefault := normalizeCodexModel(resolveOpenAIForwardModel(account, "claude-opus-4-6", ""))
-	if withoutDefault != "gpt-5.1" {
-		t.Fatalf("normalizeCodexModel(...) = %q, want %q", withoutDefault, "gpt-5.1")
+	if withoutDefault != "gpt-5.4" {
+		t.Fatalf("normalizeCodexModel(...) = %q, want %q", withoutDefault, "gpt-5.4")
 	}
 
 	withDefault := normalizeCodexModel(resolveOpenAIForwardModel(account, "claude-opus-4-6", "gpt-5.4"))
@@ -87,9 +87,9 @@ func TestResolveOpenAIForwardModel_PreventsClaudeModelFromFallingBackToGpt51(t *
 
 func TestNormalizeCodexModel(t *testing.T) {
 	cases := map[string]string{
-		"gpt-5.3-codex-spark":       "gpt-5.3-codex",
-		"gpt-5.3-codex-spark-high":  "gpt-5.3-codex",
-		"gpt-5.3-codex-spark-xhigh": "gpt-5.3-codex",
+		"gpt-5.3-codex-spark":       "gpt-5.3-codex-spark",
+		"gpt-5.3-codex-spark-high":  "gpt-5.3-codex-spark",
+		"gpt-5.3-codex-spark-xhigh": "gpt-5.3-codex-spark",
 		"gpt-5.3":                   "gpt-5.3-codex",
 	}
 
@@ -111,7 +111,7 @@ func TestNormalizeOpenAIModelForUpstream(t *testing.T) {
 			name:    "oauth keeps codex normalization behavior",
 			account: &Account{Type: AccountTypeOAuth},
 			model:   "gemini-3-flash-preview",
-			want:    "gpt-5.1",
+			want:    "gpt-5.4",
 		},
 		{
 			name:    "apikey preserves custom compatible model",
diff --git a/frontend/src/components/keys/UseKeyModal.vue b/frontend/src/components/keys/UseKeyModal.vue
index 7770e658..b3679107 100644
--- a/frontend/src/components/keys/UseKeyModal.vue
+++ b/frontend/src/components/keys/UseKeyModal.vue
@@ -617,66 +617,6 @@ function generateOpenCodeConfig(platform: string, baseUrl: string, apiKey: strin
     }
   }
   const openaiModels = {
-    'gpt-5-codex': {
-      name: 'GPT-5 Codex',
-      limit: {
-        context: 400000,
-        output: 128000
-      },
-      options: {
-        store: false
-      },
-      variants: {
-        low: {},
-        medium: {},
-        high: {}
-      }
-    },
-    'gpt-5.1-codex': {
-      name: 'GPT-5.1 Codex',
-      limit: {
-        context: 400000,
-        output: 128000
-      },
-      options: {
-        store: false
-      },
-      variants: {
-        low: {},
-        medium: {},
-        high: {}
-      }
-    },
-    'gpt-5.1-codex-max': {
-      name: 'GPT-5.1 Codex Max',
-      limit: {
-        context: 400000,
-        output: 128000
-      },
-      options: {
-        store: false
-      },
-      variants: {
-        low: {},
-        medium: {},
-        high: {}
-      }
-    },
-    'gpt-5.1-codex-mini': {
-      name: 'GPT-5.1 Codex Mini',
-      limit: {
-        context: 400000,
-        output: 128000
-      },
-      options: {
-        store: false
-      },
-      variants: {
-        low: {},
-        medium: {},
-        high: {}
-      }
-    },
     'gpt-5.2': {
       name: 'GPT-5.2',
       limit: {
@@ -725,22 +665,6 @@ function generateOpenCodeConfig(platform: string, baseUrl: string, apiKey: strin
         xhigh: {}
       }
     },
-    'gpt-5.4-nano': {
-      name: 'GPT-5.4 Nano',
-      limit: {
-        context: 400000,
-        output: 128000
-      },
-      options: {
-        store: false
-      },
-      variants: {
-        low: {},
-        medium: {},
-        high: {},
-        xhigh: {}
-      }
-    },
     'gpt-5.3-codex-spark': {
       name: 'GPT-5.3 Codex Spark',
       limit: {
@@ -773,22 +697,6 @@ function generateOpenCodeConfig(platform: string, baseUrl: string, apiKey: strin
         xhigh: {}
       }
     },
-    'gpt-5.2-codex': {
-      name: 'GPT-5.2 Codex',
-      limit: {
-        context: 400000,
-        output: 128000
-      },
-      options: {
-        store: false
-      },
-      variants: {
-        low: {},
-        medium: {},
-        high: {},
-        xhigh: {}
-      }
-    },
     'codex-mini-latest': {
       name: 'Codex Mini',
       limit: {
diff --git a/frontend/src/components/keys/__tests__/UseKeyModal.spec.ts b/frontend/src/components/keys/__tests__/UseKeyModal.spec.ts
index 98b5dede..f7db586a 100644
--- a/frontend/src/components/keys/__tests__/UseKeyModal.spec.ts
+++ b/frontend/src/components/keys/__tests__/UseKeyModal.spec.ts
@@ -17,7 +17,7 @@ vi.mock('@/composables/useClipboard', () => ({
 import UseKeyModal from '../UseKeyModal.vue'
 
 describe('UseKeyModal', () => {
-  it('renders updated GPT-5.4 mini/nano names in OpenCode config', async () => {
+  it('renders GPT-5.4 mini entry in OpenCode config', async () => {
     const wrapper = mount(UseKeyModal, {
       props: {
         show: true,
@@ -48,6 +48,6 @@ describe('UseKeyModal', () => {
     const codeBlock = wrapper.find('pre code')
     expect(codeBlock.exists()).toBe(true)
     expect(codeBlock.text()).toContain('"name": "GPT-5.4 Mini"')
-    expect(codeBlock.text()).toContain('"name": "GPT-5.4 Nano"')
+    expect(codeBlock.text()).not.toContain('"name": "GPT-5.4 Nano"')
   })
 })
diff --git a/frontend/src/composables/__tests__/useModelWhitelist.spec.ts b/frontend/src/composables/__tests__/useModelWhitelist.spec.ts
index 4061be4d..d35e3b12 100644
--- a/frontend/src/composables/__tests__/useModelWhitelist.spec.ts
+++ b/frontend/src/composables/__tests__/useModelWhitelist.spec.ts
@@ -12,10 +12,20 @@ describe('useModelWhitelist', () => {
 
     expect(models).toContain('gpt-5.4')
     expect(models).toContain('gpt-5.4-mini')
-    expect(models).toContain('gpt-5.4-nano')
     expect(models).toContain('gpt-5.4-2026-03-05')
   })
 
+  it('openai 模型列表不再暴露已下线的 ChatGPT 登录 Codex 模型', () => {
+    const models = getModelsByPlatform('openai')
+
+    expect(models).not.toContain('gpt-5')
+    expect(models).not.toContain('gpt-5.1')
+    expect(models).not.toContain('gpt-5.1-codex')
+    expect(models).not.toContain('gpt-5.1-codex-max')
+    expect(models).not.toContain('gpt-5.1-codex-mini')
+    expect(models).not.toContain('gpt-5.2-codex')
+  })
+
   it('antigravity 模型列表包含图片模型兼容项', () => {
     const models = getModelsByPlatform('antigravity')
 
@@ -55,12 +65,11 @@ describe('useModelWhitelist', () => {
     })
   })
 
-  it('whitelist keeps GPT-5.4 mini and nano exact mappings', () => {
-    const mapping = buildModelMappingObject('whitelist', ['gpt-5.4-mini', 'gpt-5.4-nano'], [])
+  it('whitelist keeps GPT-5.4 mini exact mappings', () => {
+    const mapping = buildModelMappingObject('whitelist', ['gpt-5.4-mini'], [])
 
     expect(mapping).toEqual({
-      'gpt-5.4-mini': 'gpt-5.4-mini',
-      'gpt-5.4-nano': 'gpt-5.4-nano'
+      'gpt-5.4-mini': 'gpt-5.4-mini'
     })
   })
 })
diff --git a/frontend/src/composables/useModelWhitelist.ts b/frontend/src/composables/useModelWhitelist.ts
index a282ae7d..ddd7af48 100644
--- a/frontend/src/composables/useModelWhitelist.ts
+++ b/frontend/src/composables/useModelWhitelist.ts
@@ -13,19 +13,11 @@ const openaiModels = [
   'o1', 'o1-preview', 'o1-mini', 'o1-pro',
   'o3', 'o3-mini', 'o3-pro',
   'o4-mini',
-  // GPT-5 系列（同步后端定价文件）
-  'gpt-5', 'gpt-5-2025-08-07', 'gpt-5-chat', 'gpt-5-chat-latest',
-  'gpt-5-codex', 'gpt-5.3-codex-spark', 'gpt-5-pro', 'gpt-5-pro-2025-10-06',
-  'gpt-5-mini', 'gpt-5-mini-2025-08-07',
-  'gpt-5-nano', 'gpt-5-nano-2025-08-07',
-  // GPT-5.1 系列
-  'gpt-5.1', 'gpt-5.1-2025-11-13', 'gpt-5.1-chat-latest',
-  'gpt-5.1-codex', 'gpt-5.1-codex-max', 'gpt-5.1-codex-mini',
   // GPT-5.2 系列
   'gpt-5.2', 'gpt-5.2-2025-12-11', 'gpt-5.2-chat-latest',
-  'gpt-5.2-codex', 'gpt-5.2-pro', 'gpt-5.2-pro-2025-12-11',
+  'gpt-5.2-pro', 'gpt-5.2-pro-2025-12-11',
   // GPT-5.4 系列
-  'gpt-5.4', 'gpt-5.4-mini', 'gpt-5.4-nano', 'gpt-5.4-2026-03-05',
+  'gpt-5.4', 'gpt-5.4-mini', 'gpt-5.4-2026-03-05',
   // GPT-5.3 系列
   'gpt-5.3-codex', 'gpt-5.3-codex-spark',
   'chatgpt-4o-latest',
@@ -264,12 +256,9 @@ const openaiPresetMappings = [
   { label: 'GPT-4.1', from: 'gpt-4.1', to: 'gpt-4.1', color: 'bg-indigo-100 text-indigo-700 hover:bg-indigo-200 dark:bg-indigo-900/30 dark:text-indigo-400' },
   { label: 'o1', from: 'o1', to: 'o1', color: 'bg-purple-100 text-purple-700 hover:bg-purple-200 dark:bg-purple-900/30 dark:text-purple-400' },
   { label: 'o3', from: 'o3', to: 'o3', color: 'bg-emerald-100 text-emerald-700 hover:bg-emerald-200 dark:bg-emerald-900/30 dark:text-emerald-400' },
-  { label: 'GPT-5', from: 'gpt-5', to: 'gpt-5', color: 'bg-amber-100 text-amber-700 hover:bg-amber-200 dark:bg-amber-900/30 dark:text-amber-400' },
   { label: 'GPT-5.3 Codex Spark', from: 'gpt-5.3-codex-spark', to: 'gpt-5.3-codex-spark', color: 'bg-teal-100 text-teal-700 hover:bg-teal-200 dark:bg-teal-900/30 dark:text-teal-400' },
-  { label: 'GPT-5.1', from: 'gpt-5.1', to: 'gpt-5.1', color: 'bg-orange-100 text-orange-700 hover:bg-orange-200 dark:bg-orange-900/30 dark:text-orange-400' },
   { label: 'GPT-5.2', from: 'gpt-5.2', to: 'gpt-5.2', color: 'bg-red-100 text-red-700 hover:bg-red-200 dark:bg-red-900/30 dark:text-red-400' },
   { label: 'GPT-5.4', from: 'gpt-5.4', to: 'gpt-5.4', color: 'bg-rose-100 text-rose-700 hover:bg-rose-200 dark:bg-rose-900/30 dark:text-rose-400' },
-  { label: 'GPT-5.1 Codex', from: 'gpt-5.1-codex', to: 'gpt-5.1-codex', color: 'bg-cyan-100 text-cyan-700 hover:bg-cyan-200 dark:bg-cyan-900/30 dark:text-cyan-400' },
   { label: 'Haiku→5.4', from: 'claude-haiku-4-5-20251001', to: 'gpt-5.4', color: 'bg-emerald-100 text-emerald-700 hover:bg-emerald-200 dark:bg-emerald-900/30 dark:text-emerald-400' },
   { label: 'Opus→5.4', from: 'claude-opus-4-6', to: 'gpt-5.4', color: 'bg-purple-100 text-purple-700 hover:bg-purple-200 dark:bg-purple-900/30 dark:text-purple-400' },
   { label: 'Sonnet→5.4', from: 'claude-sonnet-4-6', to: 'gpt-5.4', color: 'bg-blue-100 text-blue-700 hover:bg-blue-200 dark:bg-blue-900/30 dark:text-blue-400' }