diff --git a/CHANGELOG.md b/CHANGELOG.md
index cc28cad806f..2daf64f2fd4 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -76,6 +76,7 @@ Docs: https://docs.openclaw.ai
 - Model selection: include the rejected provider/model ref and allowlist recovery hint when a stored session override is cleared, so local model selections such as Gemma GGUF variants do not fall back to the default with a generic message. Refs #71069. Thanks @CyberRaccoonTeam.
 - OpenAI-compatible providers: drop malformed event-only or blank-data SSE frames before the OpenAI SDK stream parser sees them, so proxies that split `event:` from `data:` no longer crash streaming runs with `Unexpected end of JSON input`. Fixes #52802. Thanks @LyHug.
 - Gateway/OpenAI-compatible streaming: strip `<final>` tags split across streamed model deltas before they reach SSE clients, so `/v1/chat/completions` no longer emits tag remnants or drops content when final-answer wrappers cross chunk boundaries. Fixes #63325. Thanks @tzwickl.
+- Ollama: resolve explicitly selected signed-in `:cloud` models through `/api/show` when `/api/tags` omits them, so working models such as `gemini-3-flash-preview:cloud` and `deepseek-v4-pro:cloud` do not fail dynamic model resolution before the native `/api/chat` transport runs. Fixes #73909. Thanks @chtse53.
 - Local model prompt caching: keep stable Project Context above volatile channel/session prompt guidance and stop embedding current channel names in the message tool description, so Ollama, MLX, llama.cpp, and other prefix-cache backends avoid avoidable full prompt reprocessing across channel turns. Fixes #40256; supersedes #40296. Thanks @rhclaw and @sriram369.
 - Gateway/OpenAI-compatible API: guard provider policy lookup against runtime providers with non-array `models` values, so `/v1/chat/completions` no longer fails with `provider?.models?.some is not a function`. Fixes #66744; carries forward #66761. Thanks @MightyMoud, @MukundaKatta.
 - WhatsApp/Web: pass explicit Baileys socket timings into every WhatsApp Web socket and expose `web.whatsapp.*` keepalive, connect, and query timeout settings so unstable networks can avoid repeated 408 disconnect and opening-handshake timeout loops. Fixes #56365. (#73580) Thanks @velvet-shark.
diff --git a/docs/providers/ollama.md b/docs/providers/ollama.md
index 321bdd53e6f..417bd99c240 100644
--- a/docs/providers/ollama.md
+++ b/docs/providers/ollama.md
@@ -192,6 +192,12 @@ When you set `OLLAMA_API_KEY` (or an auth profile) and **do not** define `models
 
 This avoids manual model entries while keeping the catalog aligned with the local Ollama instance. You can use a full ref such as `ollama/<pulled-model>:latest` in local `infer model run`; OpenClaw resolves that installed model from Ollama's live catalog without requiring a hand-written `models.json` entry.
 
+For signed-in Ollama hosts, some `:cloud` models may be usable through `/api/chat`
+and `/api/show` before they appear in `/api/tags`. When you explicitly select a
+full `ollama/<model>:cloud` ref, OpenClaw validates that exact missing model with
+`/api/show` and adds it to the runtime catalog only if Ollama confirms model
+metadata. Typos still fail as unknown models instead of being auto-created.
+
 ```bash
 # See what models are available
 ollama list
diff --git a/extensions/ollama/index.test.ts b/extensions/ollama/index.test.ts
index 46db238f598..950b03daf7c 100644
--- a/extensions/ollama/index.test.ts
+++ b/extensions/ollama/index.test.ts
@@ -20,6 +20,21 @@ const promptAndConfigureOllamaMock = vi.hoisted(() =>
 );
 const ensureOllamaModelPulledMock = vi.hoisted(() => vi.fn(async () => {}));
 const buildOllamaProviderMock = vi.hoisted(() => vi.fn());
+const queryOllamaModelShowInfoMock = vi.hoisted(() => vi.fn());
+const buildOllamaModelDefinitionMock = vi.hoisted(() =>
+  vi.fn((modelId: string, contextWindow?: number, capabilities?: string[]) => ({
+    id: modelId,
+    name: modelId,
+    reasoning: capabilities?.includes("thinking") ?? false,
+    input: capabilities?.includes("vision") ? ["text", "image"] : ["text"],
+    cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+    contextWindow: contextWindow ?? 8192,
+    maxTokens: 8192,
+    compat: capabilities
+      ? { supportsTools: capabilities.includes("tools"), supportsUsageInStreaming: true }
+      : { supportsUsageInStreaming: true },
+  })),
+);
 const createConfiguredOllamaStreamFnMock = vi.hoisted(() =>
   vi.fn((_params: { model: unknown; providerBaseUrl?: string }) => ({}) as never),
 );
@@ -29,6 +44,8 @@ vi.mock("./api.js", () => ({
   ensureOllamaModelPulled: ensureOllamaModelPulledMock,
   configureOllamaNonInteractive: vi.fn(),
   buildOllamaProvider: buildOllamaProviderMock,
+  queryOllamaModelShowInfo: queryOllamaModelShowInfoMock,
+  buildOllamaModelDefinition: buildOllamaModelDefinitionMock,
 }));
 
 vi.mock("./src/stream.js", async (importOriginal) => {
@@ -43,6 +60,8 @@ beforeEach(() => {
   promptAndConfigureOllamaMock.mockClear();
   ensureOllamaModelPulledMock.mockClear();
   buildOllamaProviderMock.mockReset();
+  queryOllamaModelShowInfoMock.mockReset();
+  buildOllamaModelDefinitionMock.mockClear();
   createConfiguredOllamaStreamFnMock.mockClear();
 });
 
@@ -420,6 +439,102 @@ describe("ollama plugin", () => {
     }
   });
 
+  it("resolves requested Ollama cloud models that are omitted from tags but confirmed by show", async () => {
+    const provider = registerProvider();
+    const previous = process.env.OLLAMA_API_KEY;
+    process.env.OLLAMA_API_KEY = "ollama-local";
+    buildOllamaProviderMock.mockResolvedValueOnce({
+      baseUrl: "http://127.0.0.1:11434",
+      api: "ollama",
+      models: [
+        {
+          id: "kimi-k2.5:cloud",
+          name: "kimi-k2.5:cloud",
+          reasoning: true,
+          input: ["text"],
+          cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+          contextWindow: 262144,
+          maxTokens: 8192,
+        },
+      ],
+    });
+    queryOllamaModelShowInfoMock.mockResolvedValueOnce({
+      contextWindow: 1048576,
+      capabilities: ["completion", "tools", "thinking"],
+    });
+
+    try {
+      await provider.prepareDynamicModel?.({
+        config: {},
+        provider: "ollama",
+        modelId: "deepseek-v4-pro:cloud",
+        modelRegistry: { find: vi.fn(() => null) },
+      } as never);
+
+      expect(queryOllamaModelShowInfoMock).toHaveBeenCalledWith(
+        "http://127.0.0.1:11434",
+        "deepseek-v4-pro:cloud",
+      );
+      expect(
+        provider.resolveDynamicModel?.({
+          config: {},
+          provider: "ollama",
+          modelId: "deepseek-v4-pro:cloud",
+          modelRegistry: { find: vi.fn(() => null) },
+        } as never),
+      ).toMatchObject({
+        provider: "ollama",
+        id: "deepseek-v4-pro:cloud",
+        api: "ollama",
+        baseUrl: "http://127.0.0.1:11434",
+        reasoning: true,
+        compat: { supportsTools: true },
+      });
+    } finally {
+      if (previous === undefined) {
+        delete process.env.OLLAMA_API_KEY;
+      } else {
+        process.env.OLLAMA_API_KEY = previous;
+      }
+    }
+  });
+
+  it("keeps unknown requested Ollama models unresolved when show has no metadata", async () => {
+    const provider = registerProvider();
+    const previous = process.env.OLLAMA_API_KEY;
+    process.env.OLLAMA_API_KEY = "ollama-local";
+    buildOllamaProviderMock.mockResolvedValueOnce({
+      baseUrl: "http://127.0.0.1:11434",
+      api: "ollama",
+      models: [],
+    });
+    queryOllamaModelShowInfoMock.mockResolvedValueOnce({});
+
+    try {
+      await provider.prepareDynamicModel?.({
+        config: {},
+        provider: "ollama",
+        modelId: "depseek-v4-pro:cloud",
+        modelRegistry: { find: vi.fn(() => null) },
+      } as never);
+
+      expect(
+        provider.resolveDynamicModel?.({
+          config: {},
+          provider: "ollama",
+          modelId: "depseek-v4-pro:cloud",
+          modelRegistry: { find: vi.fn(() => null) },
+        } as never),
+      ).toBeUndefined();
+    } finally {
+      if (previous === undefined) {
+        delete process.env.OLLAMA_API_KEY;
+      } else {
+        process.env.OLLAMA_API_KEY = previous;
+      }
+    }
+  });
+
   it("skips implicit localhost discovery when a custom remote Ollama provider is configured", async () => {
     const provider = registerProvider();
 
diff --git a/extensions/ollama/index.ts b/extensions/ollama/index.ts
index 46b55691e2b..1621f364388 100644
--- a/extensions/ollama/index.ts
+++ b/extensions/ollama/index.ts
@@ -19,10 +19,13 @@ import {
   OPENAI_COMPATIBLE_REPLAY_HOOKS,
 } from "openclaw/plugin-sdk/provider-model-shared";
 import {
+  OLLAMA_DEFAULT_BASE_URL,
+  buildOllamaModelDefinition,
   buildOllamaProvider,
   configureOllamaNonInteractive,
   ensureOllamaModelPulled,
   promptAndConfigureOllama,
+  queryOllamaModelShowInfo,
 } from "./api.js";
 import {
   OLLAMA_DEFAULT_API_KEY,
@@ -100,6 +103,29 @@ function toDynamicOllamaModel(params: {
   };
 }
 
+async function resolveRequestedDynamicOllamaModel(params: {
+  provider: string;
+  providerConfig: ModelProviderConfig;
+  modelId: string;
+}): Promise<ProviderRuntimeModel | undefined> {
+  const showInfo = await queryOllamaModelShowInfo(
+    readProviderBaseUrl(params.providerConfig) ?? OLLAMA_DEFAULT_BASE_URL,
+    params.modelId,
+  );
+  if (typeof showInfo.contextWindow !== "number" && (showInfo.capabilities?.length ?? 0) === 0) {
+    return undefined;
+  }
+  return toDynamicOllamaModel({
+    provider: params.provider,
+    providerConfig: params.providerConfig,
+    model: buildOllamaModelDefinition(
+      params.modelId,
+      showInfo.contextWindow,
+      showInfo.capabilities,
+    ),
+  });
+}
+
 export default definePluginEntry({
   id: "ollama",
   name: "Ollama Provider",
@@ -268,16 +294,24 @@ export default definePluginEntry({
         }
         const baseUrl = readProviderBaseUrl(providerConfig);
         const provider = await buildOllamaProvider(baseUrl, { quiet: true });
-        dynamicModelCache.set(
-          buildDynamicCacheKey(ctx.provider, baseUrl),
-          (provider.models ?? []).map((model) =>
-            toDynamicOllamaModel({
-              provider: ctx.provider,
-              providerConfig: provider,
-              model,
-            }),
-          ),
+        const dynamicModels = (provider.models ?? []).map((model) =>
+          toDynamicOllamaModel({
+            provider: ctx.provider,
+            providerConfig: provider,
+            model,
+          }),
         );
+        if (!dynamicModels.some((model) => model.id === ctx.modelId)) {
+          const requestedModel = await resolveRequestedDynamicOllamaModel({
+            provider: ctx.provider,
+            providerConfig: provider,
+            modelId: ctx.modelId,
+          });
+          if (requestedModel) {
+            dynamicModels.push(requestedModel);
+          }
+        }
+        dynamicModelCache.set(buildDynamicCacheKey(ctx.provider, baseUrl), dynamicModels);
       },
       resolveDynamicModel: (ctx) => {
         const providerConfig = resolveConfiguredOllamaProviderConfig({