diff --git a/internal/runtime/executor/claude_executor.go b/internal/runtime/executor/claude_executor.go
index 0c31f424..2fbb235b 100644
--- a/internal/runtime/executor/claude_executor.go
+++ b/internal/runtime/executor/claude_executor.go
@@ -74,6 +74,9 @@ func (e *ClaudeExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
 	}
 	body = applyPayloadConfig(e.cfg, req.Model, body)
 
+	// Disable thinking if tool_choice forces tool use (Anthropic API constraint)
+	body = disableThinkingIfToolChoiceForced(body)
+
 	// Ensure max_tokens > thinking.budget_tokens when thinking is enabled
 	body = ensureMaxTokensForThinking(req.Model, body)
 
@@ -185,6 +188,9 @@ func (e *ClaudeExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
 	body = checkSystemInstructions(body)
 	body = applyPayloadConfig(e.cfg, req.Model, body)
 
+	// Disable thinking if tool_choice forces tool use (Anthropic API constraint)
+	body = disableThinkingIfToolChoiceForced(body)
+
 	// Ensure max_tokens > thinking.budget_tokens when thinking is enabled
 	body = ensureMaxTokensForThinking(req.Model, body)
 
@@ -461,6 +467,19 @@ func (e *ClaudeExecutor) injectThinkingConfig(modelName string, metadata map[str
 	return util.ApplyClaudeThinkingConfig(body, budget)
 }
 
+// disableThinkingIfToolChoiceForced checks if tool_choice forces tool use and disables thinking.
+// Anthropic API does not allow thinking when tool_choice is set to "any" or a specific tool.
+// See: https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking#important-considerations
+func disableThinkingIfToolChoiceForced(body []byte) []byte {
+	toolChoiceType := gjson.GetBytes(body, "tool_choice.type").String()
+	// "auto" is allowed with thinking, but "any" or "tool" (specific tool) are not
+	if toolChoiceType == "any" || toolChoiceType == "tool" {
+		// Remove thinking configuration entirely to avoid API error
+		body, _ = sjson.DeleteBytes(body, "thinking")
+	}
+	return body
+}
+
 // ensureMaxTokensForThinking ensures max_tokens > thinking.budget_tokens when thinking is enabled.
 // Anthropic API requires this constraint; violating it returns a 400 error.
 // This function should be called after all thinking configuration is finalized.