diff --git a/internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go b/internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go
index 6892f67b..5da6c2c6 100644
--- a/internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go
+++ b/internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go
@@ -34,7 +34,7 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 
 	// Reasoning effort -> thinkingBudget/include_thoughts
 	re := gjson.GetBytes(rawJSON, "reasoning_effort")
-	if re.Exists() {
+	if re.Exists() && util.ModelSupportsThinking(modelName) {
 		switch re.String() {
 		case "none":
 			out, _ = sjson.DeleteBytes(out, "request.generationConfig.thinkingConfig.include_thoughts")
@@ -42,11 +42,11 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 		case "auto":
 			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
 		case "low":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", 1024)
+			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 1024))
 		case "medium":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", 8192)
+			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 8192))
 		case "high":
-			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", 24576)
+			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 32768))
 		default:
 			out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
 		}
diff --git a/internal/translator/gemini/openai/chat-completions/gemini_openai_request.go b/internal/translator/gemini/openai/chat-completions/gemini_openai_request.go
index 7597fcef..f89ec16a 100644
--- a/internal/translator/gemini/openai/chat-completions/gemini_openai_request.go
+++ b/internal/translator/gemini/openai/chat-completions/gemini_openai_request.go
@@ -34,7 +34,7 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 
 	// Reasoning effort -> thinkingBudget/include_thoughts
 	re := gjson.GetBytes(rawJSON, "reasoning_effort")
-	if re.Exists() {
+	if re.Exists() && util.ModelSupportsThinking(modelName) {
 		switch re.String() {
 		case "none":
 			out, _ = sjson.DeleteBytes(out, "generationConfig.thinkingConfig.include_thoughts")
@@ -42,11 +42,11 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 		case "auto":
 			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
 		case "low":
-			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", 1024)
+			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 1024))
 		case "medium":
-			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", 8192)
+			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 8192))
 		case "high":
-			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", 24576)
+			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 32768))
 		default:
 			out, _ = sjson.SetBytes(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
 		}
diff --git a/internal/translator/gemini/openai/responses/gemini_openai-responses_request.go b/internal/translator/gemini/openai/responses/gemini_openai-responses_request.go
index 9058bae9..b54c2730 100644
--- a/internal/translator/gemini/openai/responses/gemini_openai-responses_request.go
+++ b/internal/translator/gemini/openai/responses/gemini_openai-responses_request.go
@@ -4,6 +4,7 @@ import (
 	"bytes"
 	"strings"
 
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -242,7 +243,7 @@ func ConvertOpenAIResponsesRequestToGemini(modelName string, inputRawJSON []byte
 		out, _ = sjson.Set(out, "generationConfig.stopSequences", sequences)
 	}
 
-	if reasoningEffort := root.Get("reasoning.effort"); reasoningEffort.Exists() {
+	if reasoningEffort := root.Get("reasoning.effort"); reasoningEffort.Exists() && util.ModelSupportsThinking(modelName) {
 		switch reasoningEffort.String() {
 		case "none":
 			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", false)
@@ -250,13 +251,13 @@ func ConvertOpenAIResponsesRequestToGemini(modelName string, inputRawJSON []byte
 		case "auto":
 			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
 		case "minimal":
-			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 1024)
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 1024))
 		case "low":
-			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 4096)
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 4096))
 		case "medium":
-			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 8192)
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 8192))
 		case "high":
-			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", 24576)
+			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", util.NormalizeThinkingBudget(modelName, 32768))
 		default:
 			out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
 		}