diff --git a/.github/workflows/e2e-script.yaml b/.github/workflows/e2e-script.yaml
index 0b729fead78..177e30ff954 100644
--- a/.github/workflows/e2e-script.yaml
+++ b/.github/workflows/e2e-script.yaml
@@ -229,8 +229,8 @@ jobs:
             printf 'NEMOCLAW_E2E_USE_HOSTED_INFERENCE=1\n'
             printf 'NEMOCLAW_PROVIDER=custom\n'
             printf 'NEMOCLAW_ENDPOINT_URL=https://inference-api.nvidia.com/v1\n'
-            printf 'NEMOCLAW_MODEL=nvidia/nvidia/nemotron-3-super-v3\n'
-            printf 'NEMOCLAW_COMPAT_MODEL=nvidia/nvidia/nemotron-3-super-v3\n'
+            printf 'NEMOCLAW_MODEL=nvidia/nvidia/nemotron-3-ultra\n'
+            printf 'NEMOCLAW_COMPAT_MODEL=nvidia/nvidia/nemotron-3-ultra\n'
             printf 'NEMOCLAW_PREFERRED_API=openai-completions\n'
             printf 'COMPATIBLE_API_KEY=%s\n' "${NVIDIA_INFERENCE_API_KEY}"
           } >> "$GITHUB_ENV"
diff --git a/.github/workflows/e2e-vitest-scenarios.yaml b/.github/workflows/e2e-vitest-scenarios.yaml
index afd930af581..04415d83873 100644
--- a/.github/workflows/e2e-vitest-scenarios.yaml
+++ b/.github/workflows/e2e-vitest-scenarios.yaml
@@ -1415,8 +1415,8 @@ jobs:
           NVIDIA_INFERENCE_API_KEY: ${{ secrets.NVIDIA_INFERENCE_API_KEY }}
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
         run: |
           set -euo pipefail
@@ -2135,8 +2135,8 @@ jobs:
       NEMOCLAW_NON_INTERACTIVE: "1"
       NEMOCLAW_PROVIDER: custom
       NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-      NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-      NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+      NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+      NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
       NEMOCLAW_PREFERRED_API: openai-completions
       NEMOCLAW_SANDBOX_NAME: e2e-rebuild-hermes
       OPENSHELL_GATEWAY: nemoclaw
@@ -2218,8 +2218,8 @@ jobs:
       NEMOCLAW_NON_INTERACTIVE: "1"
       NEMOCLAW_PROVIDER: custom
       NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-      NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-      NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+      NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+      NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
       NEMOCLAW_PREFERRED_API: openai-completions
       NEMOCLAW_SANDBOX_NAME: e2e-rebuild-hermes-base
       OPENSHELL_GATEWAY: nemoclaw
@@ -2970,8 +2970,8 @@ jobs:
       NEMOCLAW_SANDBOX_NAME: "e2e-resume"
       NEMOCLAW_PROVIDER: "custom"
       NEMOCLAW_ENDPOINT_URL: "https://inference-api.nvidia.com/v1"
-      NEMOCLAW_MODEL: "nvidia/nvidia/nemotron-3-super-v3"
-      NEMOCLAW_COMPAT_MODEL: "nvidia/nvidia/nemotron-3-super-v3"
+      NEMOCLAW_MODEL: "nvidia/nvidia/nemotron-3-ultra"
+      NEMOCLAW_COMPAT_MODEL: "nvidia/nvidia/nemotron-3-ultra"
     steps:
       - uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
         with:
diff --git a/.github/workflows/nightly-e2e.yaml b/.github/workflows/nightly-e2e.yaml
index db76a3cf1bf..b47644dff88 100644
--- a/.github/workflows/nightly-e2e.yaml
+++ b/.github/workflows/nightly-e2e.yaml
@@ -468,8 +468,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -544,8 +544,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_ISSUE_4434_LIVE: "1"
@@ -1003,8 +1003,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -1301,8 +1301,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -1608,8 +1608,8 @@ jobs:
           NVIDIA_INFERENCE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           E2E_ARTIFACT_DIR: ${{ github.workspace }}/e2e-artifacts/vitest/credential-migration
@@ -1834,8 +1834,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -1847,8 +1847,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -1886,8 +1886,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -1899,8 +1899,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -1938,8 +1938,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -1951,8 +1951,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -1991,8 +1991,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -2004,8 +2004,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -2044,8 +2044,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -2058,8 +2058,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -2100,8 +2100,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -2114,8 +2114,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
@@ -2194,8 +2194,8 @@ jobs:
           NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
           NEMOCLAW_PROVIDER: custom
           NEMOCLAW_ENDPOINT_URL: https://inference-api.nvidia.com/v1
-          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-super-v3
-          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-super-v3
+          NEMOCLAW_MODEL: nvidia/nvidia/nemotron-3-ultra
+          NEMOCLAW_COMPAT_MODEL: nvidia/nvidia/nemotron-3-ultra
           NEMOCLAW_PREFERRED_API: openai-completions
           COMPATIBLE_API_KEY: ${{ (github.event_name != 'workflow_dispatch' || inputs.target_ref == '') && secrets.NVIDIA_INFERENCE_API_KEY || '' }}
           NEMOCLAW_NON_INTERACTIVE: "1"
diff --git a/src/lib/inference/onboard-probes.test.ts b/src/lib/inference/onboard-probes.test.ts
index 7230f5fef3f..14e00c29c22 100644
--- a/src/lib/inference/onboard-probes.test.ts
+++ b/src/lib/inference/onboard-probes.test.ts
@@ -293,8 +293,8 @@ describe("OpenAI-compatible inference probes", () => {
   });
 
   it("bounds the hosted compatible inference probe for the served Nemotron model", () => {
-    expect(getChatCompletionsProbePayload("nvidia/nvidia/nemotron-3-super-v3")).toEqual({
-      model: "nvidia/nvidia/nemotron-3-super-v3",
+    expect(getChatCompletionsProbePayload("nvidia/nvidia/nemotron-3-ultra")).toEqual({
+      model: "nvidia/nvidia/nemotron-3-ultra",
       messages: [{ role: "user", content: "Reply with exactly: OK" }],
       max_tokens: 8,
     });
diff --git a/src/lib/onboard/providers.ts b/src/lib/onboard/providers.ts
index 18f835cb1ba..5362ba1c897 100644
--- a/src/lib/onboard/providers.ts
+++ b/src/lib/onboard/providers.ts
@@ -26,7 +26,7 @@ const HERMES_INFERENCE_ENDPOINT_URL = "https://inference-api.nousresearch.com/v1
 const HOSTED_INFERENCE_SOURCE_ENV = "NVIDIA_INFERENCE_API_KEY";
 const HOSTED_INFERENCE_CREDENTIAL_ENV = "COMPATIBLE_API_KEY";
 const HOSTED_INFERENCE_ENDPOINT_URL = "https://inference-api.nvidia.com/v1";
-const HOSTED_INFERENCE_MODEL = "nvidia/nvidia/nemotron-3-super-v3";
+const HOSTED_INFERENCE_MODEL = "nvidia/nvidia/nemotron-3-ultra";
 
 const REMOTE_PROVIDER_CONFIG = {
   build: {
diff --git a/test/e2e-scenario/fixtures/hosted-inference.ts b/test/e2e-scenario/fixtures/hosted-inference.ts
index f46b446bf71..4efcbbddbd5 100644
--- a/test/e2e-scenario/fixtures/hosted-inference.ts
+++ b/test/e2e-scenario/fixtures/hosted-inference.ts
@@ -6,7 +6,7 @@ const HOSTED_INFERENCE_CREDENTIAL_ENV = "COMPATIBLE_API_KEY";
 const HOSTED_INFERENCE_PROVIDER = "custom";
 const HOSTED_INFERENCE_PROVIDER_NAME = "compatible-endpoint";
 const DEFAULT_HOSTED_INFERENCE_BASE_URL = "https://inference-api.nvidia.com/v1";
-const DEFAULT_HOSTED_INFERENCE_MODEL = "nvidia/nvidia/nemotron-3-super-v3";
+const DEFAULT_HOSTED_INFERENCE_MODEL = "nvidia/nvidia/nemotron-3-ultra";
 
 export interface HostedInferenceSecrets {
   required(name: string): string;
diff --git a/test/e2e-scenario/live/agent-turn-latency-helpers.ts b/test/e2e-scenario/live/agent-turn-latency-helpers.ts
index 9fde9c79fc5..327ebdfdc44 100644
--- a/test/e2e-scenario/live/agent-turn-latency-helpers.ts
+++ b/test/e2e-scenario/live/agent-turn-latency-helpers.ts
@@ -23,7 +23,7 @@ export const HERMES_SANDBOX =
 validateSandboxName(OPENCLAW_SANDBOX);
 validateSandboxName(HERMES_SANDBOX);
 const DEFAULT_NVIDIA_MODEL = "nvidia/nemotron-3-super-120b-a12b";
-const DEFAULT_COMPAT_MODEL = "nvidia/nvidia/nemotron-3-super-v3";
+const DEFAULT_COMPAT_MODEL = "nvidia/nvidia/nemotron-3-ultra";
 const USE_COMPATIBLE_HOSTED = process.env.NEMOCLAW_E2E_USE_HOSTED_INFERENCE === "1";
 export const MODEL =
   process.env.NEMOCLAW_TURN_LATENCY_MODEL ??
diff --git a/test/e2e-scenario/live/hermes-discord.test.ts b/test/e2e-scenario/live/hermes-discord.test.ts
index a64f89ff91a..d6ad565b889 100644
--- a/test/e2e-scenario/live/hermes-discord.test.ts
+++ b/test/e2e-scenario/live/hermes-discord.test.ts
@@ -47,11 +47,11 @@ function commandEnv(apiKey?: string, extra: NodeJS.ProcessEnv = {}): NodeJS.Proc
       NEMOCLAW_PROVIDER: process.env.NEMOCLAW_PROVIDER ?? "custom",
       NEMOCLAW_ENDPOINT_URL:
         process.env.NEMOCLAW_ENDPOINT_URL ?? "https://inference-api.nvidia.com/v1",
-      NEMOCLAW_MODEL: process.env.NEMOCLAW_MODEL ?? "nvidia/nvidia/nemotron-3-super-v3",
+      NEMOCLAW_MODEL: process.env.NEMOCLAW_MODEL ?? "nvidia/nvidia/nemotron-3-ultra",
       NEMOCLAW_COMPAT_MODEL:
         process.env.NEMOCLAW_COMPAT_MODEL ??
         process.env.NEMOCLAW_MODEL ??
-        "nvidia/nvidia/nemotron-3-super-v3",
+        "nvidia/nvidia/nemotron-3-ultra",
       NEMOCLAW_PREFERRED_API: process.env.NEMOCLAW_PREFERRED_API ?? "openai-completions",
       DISCORD_BOT_TOKEN: DISCORD_TOKEN,
       DISCORD_SERVER_IDS,
diff --git a/test/e2e-scenario/live/hermes-slack-e2e-helpers.ts b/test/e2e-scenario/live/hermes-slack-e2e-helpers.ts
index 695ba57e9bd..adf999f6d94 100644
--- a/test/e2e-scenario/live/hermes-slack-e2e-helpers.ts
+++ b/test/e2e-scenario/live/hermes-slack-e2e-helpers.ts
@@ -40,12 +40,11 @@ function hermesSlackEnv(apiKey?: string): NodeJS.ProcessEnv {
     apiKey,
     extra: {
       ...(apiKey ? { COMPATIBLE_API_KEY: apiKey } : {}),
-      NEMOCLAW_COMPAT_MODEL:
-        process.env.NEMOCLAW_COMPAT_MODEL ?? "nvidia/nvidia/nemotron-3-super-v3",
+      NEMOCLAW_COMPAT_MODEL: process.env.NEMOCLAW_COMPAT_MODEL ?? "nvidia/nvidia/nemotron-3-ultra",
       NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1",
       NEMOCLAW_ENDPOINT_URL:
         process.env.NEMOCLAW_ENDPOINT_URL ?? "https://inference-api.nvidia.com/v1",
-      NEMOCLAW_MODEL: process.env.NEMOCLAW_MODEL ?? "nvidia/nvidia/nemotron-3-super-v3",
+      NEMOCLAW_MODEL: process.env.NEMOCLAW_MODEL ?? "nvidia/nvidia/nemotron-3-ultra",
       NEMOCLAW_POLICY_TIER: process.env.NEMOCLAW_POLICY_TIER ?? "open",
       NEMOCLAW_PREFERRED_API: process.env.NEMOCLAW_PREFERRED_API ?? "openai-completions",
       NEMOCLAW_PROVIDER: process.env.NEMOCLAW_PROVIDER ?? "custom",
diff --git a/test/e2e-scenario/live/rebuild-hermes.test.ts b/test/e2e-scenario/live/rebuild-hermes.test.ts
index c5ee26333d2..2df0fe7b052 100644
--- a/test/e2e-scenario/live/rebuild-hermes.test.ts
+++ b/test/e2e-scenario/live/rebuild-hermes.test.ts
@@ -56,7 +56,7 @@ const HOSTED_ENDPOINT_URL =
 const HOSTED_MODEL =
   process.env.NEMOCLAW_MODEL ??
   process.env.NEMOCLAW_COMPAT_MODEL ??
-  "nvidia/nvidia/nemotron-3-super-v3";
+  "nvidia/nvidia/nemotron-3-ultra";
 const OLD_BASE_TAG = `nemoclaw-hermes-old-base:${SANDBOX_NAME.toLowerCase().replace(/[^a-z0-9_.-]+/g, "-")}`;
 const CURRENT_BASE_TAG = "ghcr.io/nvidia/nemoclaw/hermes-sandbox-base:latest";
 
diff --git a/test/e2e-scenario/live/upgrade-stale-sandbox-helpers.ts b/test/e2e-scenario/live/upgrade-stale-sandbox-helpers.ts
index 9e49e87e438..8b6fecc2ffb 100644
--- a/test/e2e-scenario/live/upgrade-stale-sandbox-helpers.ts
+++ b/test/e2e-scenario/live/upgrade-stale-sandbox-helpers.ts
@@ -122,7 +122,7 @@ export function writeStaleRegistryEntry(): void {
     (typeof session.model === "string" && session.model) ||
     process.env.NEMOCLAW_MODEL ||
     process.env.NEMOCLAW_COMPAT_MODEL ||
-    "nvidia/nvidia/nemotron-3-super-v3";
+    "nvidia/nvidia/nemotron-3-ultra";
   const registry = readJsonFile<{
     sandboxes?: Record<string, Record<string, unknown>>;
     defaultSandbox?: string;
diff --git a/test/e2e-script-workflow.test.ts b/test/e2e-script-workflow.test.ts
index 1da46728c7b..f966b53f988 100644
--- a/test/e2e-script-workflow.test.ts
+++ b/test/e2e-script-workflow.test.ts
@@ -546,8 +546,8 @@ describe("E2E reusable workflow contract", () => {
     expect(runStep?.env?.NVIDIA_INFERENCE_API_KEY).toBe(GUARDED_HOSTED_INFERENCE_SECRET);
     expect(runStep?.env?.NEMOCLAW_PROVIDER).toBe("custom");
     expect(runStep?.env?.NEMOCLAW_ENDPOINT_URL).toBe("https://inference-api.nvidia.com/v1");
-    expect(runStep?.env?.NEMOCLAW_MODEL).toBe("nvidia/nvidia/nemotron-3-super-v3");
-    expect(runStep?.env?.NEMOCLAW_COMPAT_MODEL).toBe("nvidia/nvidia/nemotron-3-super-v3");
+    expect(runStep?.env?.NEMOCLAW_MODEL).toBe("nvidia/nvidia/nemotron-3-ultra");
+    expect(runStep?.env?.NEMOCLAW_COMPAT_MODEL).toBe("nvidia/nvidia/nemotron-3-ultra");
     expect(runStep?.env?.NEMOCLAW_PREFERRED_API).toBe("openai-completions");
     expect(runStep?.env?.COMPATIBLE_API_KEY).toBe(GUARDED_HOSTED_INFERENCE_SECRET);
     expect(runStep?.env?.GITHUB_TOKEN).toBeUndefined();
@@ -926,8 +926,8 @@ describe("E2E reusable workflow contract", () => {
     expect(exportStep?.run).toContain("NEMOCLAW_E2E_USE_HOSTED_INFERENCE=1");
     expect(exportStep?.run).toContain("NEMOCLAW_PROVIDER=custom");
     expect(exportStep?.run).toContain("NEMOCLAW_ENDPOINT_URL=https://inference-api.nvidia.com/v1");
-    expect(exportStep?.run).toContain("NEMOCLAW_MODEL=nvidia/nvidia/nemotron-3-super-v3");
-    expect(exportStep?.run).toContain("NEMOCLAW_COMPAT_MODEL=nvidia/nvidia/nemotron-3-super-v3");
+    expect(exportStep?.run).toContain("NEMOCLAW_MODEL=nvidia/nvidia/nemotron-3-ultra");
+    expect(exportStep?.run).toContain("NEMOCLAW_COMPAT_MODEL=nvidia/nvidia/nemotron-3-ultra");
     expect(exportStep?.run).toContain("NEMOCLAW_PREFERRED_API=openai-completions");
     expect(exportStep?.run).toContain("COMPATIBLE_API_KEY=%s");
 
@@ -950,7 +950,7 @@ describe("E2E reusable workflow contract", () => {
       expect(body, fixture).toContain("if env_provider == 'custom'");
       expect(body, fixture).toContain("'provider': provider");
       expect(body, fixture).toContain("'model': model");
-      expect(body, fixture).toContain("nvidia/nvidia/nemotron-3-super-v3");
+      expect(body, fixture).toContain("nvidia/nvidia/nemotron-3-ultra");
       expect(body, fixture).not.toContain("'provider': 'nvidia-prod'");
       expect(body, fixture).not.toContain("'model': 'nvidia/nemotron-3-super-120b-a12b'");
     }
@@ -1003,8 +1003,8 @@ describe("E2E reusable workflow contract", () => {
       }
       expect(step.env?.NEMOCLAW_PROVIDER, jobName).toBe("custom");
       expect(step.env?.NEMOCLAW_ENDPOINT_URL, jobName).toBe("https://inference-api.nvidia.com/v1");
-      expect(step.env?.NEMOCLAW_MODEL, jobName).toBe("nvidia/nvidia/nemotron-3-super-v3");
-      expect(step.env?.NEMOCLAW_COMPAT_MODEL, jobName).toBe("nvidia/nvidia/nemotron-3-super-v3");
+      expect(step.env?.NEMOCLAW_MODEL, jobName).toBe("nvidia/nvidia/nemotron-3-ultra");
+      expect(step.env?.NEMOCLAW_COMPAT_MODEL, jobName).toBe("nvidia/nvidia/nemotron-3-ultra");
       expect(step.env?.NEMOCLAW_PREFERRED_API, jobName).toBe("openai-completions");
       expect(step.env?.COMPATIBLE_API_KEY, jobName).toBe(GUARDED_HOSTED_INFERENCE_SECRET);
     }
diff --git a/test/e2e/lib/ci-compatible-inference.sh b/test/e2e/lib/ci-compatible-inference.sh
index 01ae3c99328..12cdb94bcb1 100755
--- a/test/e2e/lib/ci-compatible-inference.sh
+++ b/test/e2e/lib/ci-compatible-inference.sh
@@ -7,7 +7,7 @@
 # at inference-api.nvidia.com. Keep this helper in test/e2e so the
 # product-facing provider/default endpoint remain unchanged.
 
-NEMOCLAW_E2E_COMPATIBLE_INFERENCE_MODEL_DEFAULT="nvidia/nvidia/nemotron-3-super-v3"
+NEMOCLAW_E2E_COMPATIBLE_INFERENCE_MODEL_DEFAULT="nvidia/nvidia/nemotron-3-ultra"
 NEMOCLAW_E2E_HOSTED_INFERENCE_PROVIDER_DEFAULT="compatible-endpoint"
 NEMOCLAW_E2E_NVIDIA_INFERENCE_MODEL_DEFAULT="nvidia/nemotron-3-super-120b-a12b"
 
diff --git a/test/e2e/test-rebuild-hermes.sh b/test/e2e/test-rebuild-hermes.sh
index a6ec7e7c0e2..f5d83266e91 100755
--- a/test/e2e/test-rebuild-hermes.sh
+++ b/test/e2e/test-rebuild-hermes.sh
@@ -261,7 +261,7 @@ model = (
     sess.get('model')
     or os.environ.get('NEMOCLAW_MODEL')
     or os.environ.get('NEMOCLAW_COMPAT_MODEL')
-    or 'nvidia/nvidia/nemotron-3-super-v3'
+    or 'nvidia/nvidia/nemotron-3-ultra'
 )
 credential_hash = hashlib.sha256('${DISCORD_FAKE_TOKEN}'.encode()).hexdigest()
 plan = {
@@ -397,7 +397,7 @@ fi
 
 # Inference works after rebuild (proves credential chain is intact)
 info "Verifying inference after rebuild..."
-POST_REBUILD_INFERENCE_MODEL="${NEMOCLAW_MODEL:-${NEMOCLAW_COMPAT_MODEL:-nvidia/nvidia/nemotron-3-super-v3}}"
+POST_REBUILD_INFERENCE_MODEL="${NEMOCLAW_MODEL:-${NEMOCLAW_COMPAT_MODEL:-nvidia/nvidia/nemotron-3-ultra}}"
 INFERENCE_RESPONSE=$(openshell sandbox exec --name "${SANDBOX_NAME}" -- \
   curl -s --max-time 60 https://inference.local/v1/chat/completions \
   -H 'Content-Type: application/json' \
diff --git a/test/e2e/test-rebuild-openclaw.sh b/test/e2e/test-rebuild-openclaw.sh
index 1cbbcc86bcd..7535602b3f9 100755
--- a/test/e2e/test-rebuild-openclaw.sh
+++ b/test/e2e/test-rebuild-openclaw.sh
@@ -230,7 +230,7 @@ model = (
     sess.get('model')
     or os.environ.get('NEMOCLAW_MODEL')
     or os.environ.get('NEMOCLAW_COMPAT_MODEL')
-    or 'nvidia/nvidia/nemotron-3-super-v3'
+    or 'nvidia/nvidia/nemotron-3-ultra'
 )
 reg = {'sandboxes': {'${SANDBOX_NAME}': {
     'name': '${SANDBOX_NAME}',
@@ -446,7 +446,7 @@ fi
 
 # Inference works after rebuild (proves credential chain is intact)
 info "Verifying inference after rebuild..."
-POST_REBUILD_INFERENCE_MODEL="${NEMOCLAW_MODEL:-${NEMOCLAW_COMPAT_MODEL:-nvidia/nvidia/nemotron-3-super-v3}}"
+POST_REBUILD_INFERENCE_MODEL="${NEMOCLAW_MODEL:-${NEMOCLAW_COMPAT_MODEL:-nvidia/nvidia/nemotron-3-ultra}}"
 INFERENCE_RESPONSE=$(openshell sandbox exec --name "${SANDBOX_NAME}" -- \
   curl -s --max-time 60 https://inference.local/v1/chat/completions \
   -H 'Content-Type: application/json' \
diff --git a/test/e2e/test-upgrade-stale-sandbox.sh b/test/e2e/test-upgrade-stale-sandbox.sh
index 9af15e7e3ff..e06c03d53b7 100755
--- a/test/e2e/test-upgrade-stale-sandbox.sh
+++ b/test/e2e/test-upgrade-stale-sandbox.sh
@@ -170,7 +170,7 @@ model = (
     sess.get('model')
     or os.environ.get('NEMOCLAW_MODEL')
     or os.environ.get('NEMOCLAW_COMPAT_MODEL')
-    or 'nvidia/nvidia/nemotron-3-super-v3'
+    or 'nvidia/nvidia/nemotron-3-ultra'
 )
 reg = {'sandboxes': {'${SANDBOX_NAME}': {
     'name': '${SANDBOX_NAME}',
diff --git a/tools/e2e-scenarios/workflow-boundary.mts b/tools/e2e-scenarios/workflow-boundary.mts
index 7fc5008d37d..6811e3bb65a 100644
--- a/tools/e2e-scenarios/workflow-boundary.mts
+++ b/tools/e2e-scenarios/workflow-boundary.mts
@@ -1771,10 +1771,10 @@ function validateRebuildHermesVitestJob(
   if (jobEnv.NEMOCLAW_ENDPOINT_URL !== "https://inference-api.nvidia.com/v1") {
     errors.push(`${jobName} job must target hosted CI inference endpoint`);
   }
-  if (jobEnv.NEMOCLAW_MODEL !== "nvidia/nvidia/nemotron-3-super-v3") {
+  if (jobEnv.NEMOCLAW_MODEL !== "nvidia/nvidia/nemotron-3-ultra") {
     errors.push(`${jobName} job must pin the CI-safe Hermes rebuild model`);
   }
-  if (jobEnv.NEMOCLAW_COMPAT_MODEL !== "nvidia/nvidia/nemotron-3-super-v3") {
+  if (jobEnv.NEMOCLAW_COMPAT_MODEL !== "nvidia/nvidia/nemotron-3-ultra") {
     errors.push(`${jobName} job must pin the CI-safe compatible model`);
   }
   if (jobEnv.OPENSHELL_GATEWAY !== "nemoclaw") {