diff --git a/cmd/membench/llm_client.go b/cmd/membench/llm_client.go
index bb0ff54c4..d32de057d 100644
--- a/cmd/membench/llm_client.go
+++ b/cmd/membench/llm_client.go
@@ -91,10 +91,7 @@ func (c *LLMClient) Complete(ctx context.Context, systemPrompt, userPrompt strin
 		return "", fmt.Errorf("marshal request: %w", err)
 	}
 
-	endpoint := c.BaseURL + "/v1/chat/completions"
-	if strings.HasSuffix(c.BaseURL, "/v1") || strings.HasSuffix(c.BaseURL, "/v1/") {
-		endpoint = strings.TrimRight(c.BaseURL, "/") + "/chat/completions"
-	}
+	endpoint := strings.TrimRight(c.BaseURL, "/") + "/chat/completions"
 	req, err := http.NewRequestWithContext(ctx, "POST", endpoint, bytes.NewReader(jsonBody))
 	if err != nil {
 		return "", fmt.Errorf("create request: %w", err)
diff --git a/cmd/membench/main.go b/cmd/membench/main.go
index 7591713a7..340924e46 100644
--- a/cmd/membench/main.go
+++ b/cmd/membench/main.go
@@ -289,13 +289,13 @@ func envOrFlag(flag, envKey string) string {
 //
 // Environment variables:
 //
-//	MEMBENCH_API_BASE  – OpenAI-compatible base URL  (default http://127.0.0.1:8080)
+//	MEMBENCH_API_BASE  – OpenAI-compatible base URL  (default http://127.0.0.1:8080/v1)
 //	MEMBENCH_API_KEY   – Bearer token for the endpoint
 //	MEMBENCH_MODEL     – Model name to send in the request
 func buildLLMOptions() (LLMClientOptions, error) {
 	base := envOrFlag(flagAPIBase, "MEMBENCH_API_BASE")
 	if base == "" {
-		base = "http://127.0.0.1:8080"
+		base = "http://127.0.0.1:8080/v1"
 	}
 	model := envOrFlag(flagModel, "MEMBENCH_MODEL")
 	if model == "" {