diff --git a/CHANGELOG.md b/CHANGELOG.md
index 7fca76efcc1..2a55b7342bf 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -12,6 +12,7 @@ Docs: https://docs.openclaw.ai
 ### Fixes
 
 - Cron/Telegram: preserve explicit `:topic:` delivery targets over stale session-derived thread IDs when isolated cron announces to Telegram forum topics. Carries forward #59069; refs #49704 and #43808. Thanks @roytong9.
+- CLI/model probes: reject empty or whitespace-only `infer model run --prompt` values before calling local providers or the Gateway, so smoke checks do not spend provider calls on invalid turns. Fixes #73185. Thanks @iot2edge.
 - Gateway/media: route text-only `chat.send` image offloads through media-understanding fields so `agents.defaults.imageModel` can describe WebChat attachments instead of leaving only an opaque `media://inbound` marker. Fixes #72968. Thanks @vorajeeah.
 - CLI/onboarding: infer image input for common custom-provider vision model IDs, ask only for unknown models, and keep `--custom-image-input`/`--custom-text-input` overrides so vision-capable proxies do not get saved as text-only configs. Fixes #51869. Thanks @Antsoldier1974.
 - Models/OpenAI Codex: stop listing or resolving unsupported `openai-codex/gpt-5.4-mini` rows through Codex OAuth, keep stale discovery rows suppressed with a clear API-key-route hint, and leave direct `openai/gpt-5.4-mini` available. Fixes #73242. Thanks @0xCyda.
diff --git a/docs/cli/infer.md b/docs/cli/infer.md
index 9203bad6b64..722f9a7fd35 100644
--- a/docs/cli/infer.md
+++ b/docs/cli/infer.md
@@ -159,6 +159,7 @@ openclaw infer model run --local --model openai/gpt-4.1 --prompt "Reply with exa
 Notes:
 
 - Local `model run` is the narrowest CLI smoke for provider/model/auth health because it sends only the supplied prompt to the selected model.
+- `model run --prompt` must contain non-whitespace text; empty prompts are rejected before local providers or the Gateway are called.
 - Local `model run` exits non-zero when the provider returns no text output, so unreachable local providers and empty completions do not look like successful probes.
 - Use `model run --gateway` when you need to test Gateway routing, agent-runtime setup, or Gateway-managed provider state instead of the lean local completion path.
 - `model auth login`, `model auth logout`, and `model auth status` manage saved provider auth state.
diff --git a/src/cli/capability-cli.test.ts b/src/cli/capability-cli.test.ts
index 09510657a6d..e473a972a9a 100644
--- a/src/cli/capability-cli.test.ts
+++ b/src/cli/capability-cli.test.ts
@@ -437,6 +437,26 @@ describe("capability cli", () => {
     expect(mocks.runtime.writeJson).not.toHaveBeenCalled();
   });
 
+  it.each(["", "   ", "\n\t"])(
+    "rejects empty model run prompts before local dispatch (%j)",
+    async (prompt) => {
+      await expect(
+        runRegisteredCli({
+          register: registerCapabilityCli as (program: Command) => void,
+          argv: ["capability", "model", "run", "--prompt", prompt, "--json"],
+        }),
+      ).rejects.toThrow("exit 1");
+
+      expect(mocks.runtime.error).toHaveBeenCalledWith(
+        expect.stringContaining("--prompt cannot be empty or whitespace-only."),
+      );
+      expect(mocks.prepareSimpleCompletionModelForAgent).not.toHaveBeenCalled();
+      expect(mocks.completeWithPreparedSimpleCompletionModel).not.toHaveBeenCalled();
+      expect(mocks.callGateway).not.toHaveBeenCalled();
+      expect(mocks.runtime.writeJson).not.toHaveBeenCalled();
+    },
+  );
+
   it("runs gateway model probes without chat-agent prompt policy or tools", async () => {
     await runRegisteredCli({
       register: registerCapabilityCli as (program: Command) => void,
@@ -455,6 +475,21 @@ describe("capability cli", () => {
     );
   });
 
+  it("rejects empty model run prompts before gateway dispatch", async () => {
+    await expect(
+      runRegisteredCli({
+        register: registerCapabilityCli as (program: Command) => void,
+        argv: ["capability", "model", "run", "--prompt", " ", "--gateway", "--json"],
+      }),
+    ).rejects.toThrow("exit 1");
+
+    expect(mocks.runtime.error).toHaveBeenCalledWith(
+      expect.stringContaining("--prompt cannot be empty or whitespace-only."),
+    );
+    expect(mocks.callGateway).not.toHaveBeenCalled();
+    expect(mocks.runtime.writeJson).not.toHaveBeenCalled();
+  });
+
   it("defaults tts status to gateway transport", async () => {
     await runRegisteredCli({
       register: registerCapabilityCli as (program: Command) => void,
diff --git a/src/cli/capability-cli.ts b/src/cli/capability-cli.ts
index a79ad3164d8..ecbb033e3b4 100644
--- a/src/cli/capability-cli.ts
+++ b/src/cli/capability-cli.ts
@@ -577,6 +577,13 @@ function collectModelRunText(content: Array<{ type: string; text?: string }>): s
     .trim();
 }
 
+function requireModelRunPrompt(value: unknown): string {
+  if (typeof value !== "string" || normalizeOptionalString(value) === undefined) {
+    throw new Error("--prompt cannot be empty or whitespace-only.");
+  }
+  return value;
+}
+
 async function runModelRun(params: {
   prompt: string;
   model?: string;
@@ -1487,6 +1494,7 @@ export function registerCapabilityCli(program: Command) {
     .option("--json", "Output JSON", false)
     .action(async (opts) => {
       await runCommandWithRuntime(defaultRuntime, async () => {
+        const prompt = requireModelRunPrompt(opts.prompt);
         const transport = resolveTransport({
           local: Boolean(opts.local),
           gateway: Boolean(opts.gateway),
@@ -1494,7 +1502,7 @@ export function registerCapabilityCli(program: Command) {
           defaultTransport: "local",
         });
         const result = await runModelRun({
-          prompt: String(opts.prompt),
+          prompt,
           model: opts.model as string | undefined,
           transport,
         });