diff --git a/CHANGELOG.md b/CHANGELOG.md
index 1e48767150e..f63ee66929e 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -12,6 +12,7 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
+- NVIDIA/NIM: persist the `NVIDIA_API_KEY` provider marker and mark bundled NVIDIA Chat Completions models as string-content compatible, so NIM models load from `models.json` and OpenAI-compatible subagent calls send plain text content. Fixes #73013 and #50107; refs #73014. Thanks @bautrey, @iot2edge, @ifearghal, and @futhgar.
 - CLI/plugins: use plugin metadata snapshots for install slot selection and add opt-in plugin lifecycle timing traces, so plugin install avoids runtime-loading the plugin registry for metadata-only decisions. Thanks @shakkernerd.
 - fix(plugins): restrict bundled plugin dir resolution to trusted package roots. (#73275) Thanks @pgondhi987.
 - fix(security): prevent workspace PATH injection via service env and trash helpers. (#73264) Thanks @pgondhi987.
diff --git a/extensions/nvidia/openclaw.plugin.json b/extensions/nvidia/openclaw.plugin.json
index ba19303de3b..7eb372a7e1d 100644
--- a/extensions/nvidia/openclaw.plugin.json
+++ b/extensions/nvidia/openclaw.plugin.json
@@ -29,6 +29,9 @@
               "output": 0,
               "cacheRead": 0,
               "cacheWrite": 0
+            },
+            "compat": {
+              "requiresStringContent": true
             }
           },
           {
@@ -42,6 +45,9 @@
               "output": 0,
               "cacheRead": 0,
               "cacheWrite": 0
+            },
+            "compat": {
+              "requiresStringContent": true
             }
           },
           {
@@ -55,6 +61,9 @@
               "output": 0,
               "cacheRead": 0,
               "cacheWrite": 0
+            },
+            "compat": {
+              "requiresStringContent": true
             }
           },
           {
@@ -68,6 +77,9 @@
               "output": 0,
               "cacheRead": 0,
               "cacheWrite": 0
+            },
+            "compat": {
+              "requiresStringContent": true
             }
           }
         ]
diff --git a/extensions/nvidia/provider-catalog.test.ts b/extensions/nvidia/provider-catalog.test.ts
index de162374b01..79139b400a3 100644
--- a/extensions/nvidia/provider-catalog.test.ts
+++ b/extensions/nvidia/provider-catalog.test.ts
@@ -7,11 +7,15 @@ describe("nvidia provider catalog", () => {
 
     expect(provider.baseUrl).toBe("https://integrate.api.nvidia.com/v1");
     expect(provider.api).toBe("openai-completions");
+    expect(provider.apiKey).toBe("NVIDIA_API_KEY");
     expect(provider.models.map((model) => model.id)).toEqual([
       "nvidia/nemotron-3-super-120b-a12b",
       "moonshotai/kimi-k2.5",
       "minimaxai/minimax-m2.5",
       "z-ai/glm5",
     ]);
+    expect(provider.models.every((model) => model.compat?.requiresStringContent === true)).toBe(
+      true,
+    );
   });
 });
diff --git a/extensions/nvidia/provider-catalog.ts b/extensions/nvidia/provider-catalog.ts
index 0c7f3b77795..d01b50c3f94 100644
--- a/extensions/nvidia/provider-catalog.ts
+++ b/extensions/nvidia/provider-catalog.ts
@@ -3,8 +3,11 @@ import type { ModelProviderConfig } from "openclaw/plugin-sdk/provider-model-sha
 import manifest from "./openclaw.plugin.json" with { type: "json" };
 
 export function buildNvidiaProvider(): ModelProviderConfig {
-  return buildManifestModelProviderConfig({
-    providerId: "nvidia",
-    catalog: manifest.modelCatalog.providers.nvidia,
-  });
+  return {
+    ...buildManifestModelProviderConfig({
+      providerId: "nvidia",
+      catalog: manifest.modelCatalog.providers.nvidia,
+    }),
+    apiKey: "NVIDIA_API_KEY",
+  };
 }