diff --git a/core/src/browser/extensions/engines/OAIEngine.ts b/core/src/browser/extensions/engines/OAIEngine.ts
index 01ef55e5e..a8dde4677 100644
--- a/core/src/browser/extensions/engines/OAIEngine.ts
+++ b/core/src/browser/extensions/engines/OAIEngine.ts
@@ -89,6 +89,7 @@ export abstract class OAIEngine extends AIEngine {
       model: model.id,
       stream: true,
       ...model.parameters,
+      ...(this.provider === 'nitro' ? { engine: 'cortex.llamacpp'} : {}),
     }
     if (this.transformPayload) {
       requestBody = this.transformPayload(requestBody)
diff --git a/extensions/inference-nitro-extension/bin/version.txt b/extensions/inference-nitro-extension/bin/version.txt
index 2b2a18d26..8f0916f76 100644
--- a/extensions/inference-nitro-extension/bin/version.txt
+++ b/extensions/inference-nitro-extension/bin/version.txt
@@ -1 +1 @@
-0.4.20
+0.5.0
diff --git a/extensions/inference-nitro-extension/download.bat b/extensions/inference-nitro-extension/download.bat
index 9bd2d4b07..b7fbd3252 100644
--- a/extensions/inference-nitro-extension/download.bat
+++ b/extensions/inference-nitro-extension/download.bat
@@ -1,3 +1,3 @@
 @echo off
 set /p CORTEX_VERSION=<./bin/version.txt
-.\node_modules\.bin\download https://github.com/janhq/cortex/releases/download/v%CORTEX_VERSION%/cortex-cpp-%CORTEX_VERSION%-windows-amd64-avx2-cuda-12-0.tar.gz -e --strip 1 -o ./bin/win-cuda-12-0 && .\node_modules\.bin\download https://github.com/janhq/cortex/releases/download/v%CORTEX_VERSION%/cortex-cpp-%CORTEX_VERSION%-windows-amd64-avx2-cuda-11-7.tar.gz -e --strip 1 -o ./bin/win-cuda-11-7 && .\node_modules\.bin\download https://github.com/janhq/nitro/releases/download/v%CORTEX_VERSION%/cortex-cpp-%CORTEX_VERSION%-windows-amd64-avx2.tar.gz -e --strip 1 -o ./bin/win-cpu && .\node_modules\.bin\download https://github.com/janhq/cortex/releases/download/v%CORTEX_VERSION%/cortex-cpp-%CORTEX_VERSION%-windows-amd64-vulkan.tar.gz -e --strip 1 -o ./bin/win-vulkan
+.\node_modules\.bin\download https://github.com/janhq/cortex/releases/download/v%CORTEX_VERSION%/cortex-cpp-%CORTEX_VERSION%-windows-amd64.tar.gz -e --strip 1 -o ./bin/win-cuda-12-0 && .\node_modules\.bin\download https://github.com/janhq/cortex/releases/download/v%CORTEX_VERSION%/cortex-cpp-%CORTEX_VERSION%-windows-amd64.tar.gz -e --strip 1 -o ./bin/win-cuda-11-7 && .\node_modules\.bin\download https://github.com/janhq/cortex/releases/download/v%CORTEX_VERSION%/cortex-cpp-%CORTEX_VERSION%-windows-amd64.tar.gz -e --strip 1 -o ./bin/win-cpu && .\node_modules\.bin\download https://github.com/janhq/cortex/releases/download/v%CORTEX_VERSION%/cortex-cpp-%CORTEX_VERSION%-windows-amd64.tar.gz -e --strip 1 -o ./bin/win-vulkan && .\node_modules\.bin\download https://github.com/janhq/cortex.llamacpp/releases/download/v0.1.25/cortex.llamacpp-0.1.25-windows-amd64-noavx-cuda-12-0.tar.gz -e --strip 1 -o ./bin/win-cuda-12-0/engines/cortex.llamacpp && .\node_modules\.bin\download https://github.com/janhq/cortex.llamacpp/releases/download/v0.1.25/cortex.llamacpp-0.1.25-windows-amd64-noavx-cuda-11-7.tar.gz -e --strip 1 -o ./bin/win-cuda-11-7/engines/cortex.llamacpp && .\node_modules\.bin\download https://github.com/janhq/cortex.llamacpp/releases/download/v0.1.25/cortex.llamacpp-0.1.25-windows-amd64-noavx.tar.gz -e --strip 1 -o ./bin/win-cpu/engines/cortex.llamacpp && .\node_modules\.bin\download https://github.com/janhq/cortex.llamacpp/releases/download/v0.1.25/cortex.llamacpp-0.1.25-windows-amd64-vulkan.tar.gz -e --strip 1 -o ./bin/win-vulkan/engines/cortex.llamacpp
diff --git a/extensions/inference-nitro-extension/package.json b/extensions/inference-nitro-extension/package.json
index 3150108c4..24c887024 100644
--- a/extensions/inference-nitro-extension/package.json
+++ b/extensions/inference-nitro-extension/package.json
@@ -10,8 +10,8 @@
   "scripts": {
     "test": "jest",
     "build": "tsc --module commonjs && rollup -c rollup.config.ts",
-    "downloadnitro:linux": "CORTEX_VERSION=$(cat ./bin/version.txt) && download https://github.com/janhq/cortex/releases/download/v${CORTEX_VERSION}/cortex-cpp-${CORTEX_VERSION}-linux-amd64-avx2.tar.gz -e --strip 1 -o ./bin/linux-cpu && chmod +x ./bin/linux-cpu/cortex-cpp && download https://github.com/janhq/cortex/releases/download/v${CORTEX_VERSION}/cortex-cpp-${CORTEX_VERSION}-linux-amd64-avx2-cuda-12-0.tar.gz -e --strip 1 -o ./bin/linux-cuda-12-0 && chmod +x ./bin/linux-cuda-12-0/cortex-cpp && download https://github.com/janhq/cortex/releases/download/v${CORTEX_VERSION}/cortex-cpp-${CORTEX_VERSION}-linux-amd64-avx2-cuda-11-7.tar.gz -e --strip 1 -o ./bin/linux-cuda-11-7 && chmod +x ./bin/linux-cuda-11-7/cortex-cpp && download https://github.com/janhq/cortex/releases/download/v${CORTEX_VERSION}/cortex-cpp-${CORTEX_VERSION}-linux-amd64-vulkan.tar.gz -e --strip 1 -o ./bin/linux-vulkan && chmod +x ./bin/linux-vulkan/cortex-cpp",
-    "downloadnitro:darwin": "CORTEX_VERSION=$(cat ./bin/version.txt) && download https://github.com/janhq/cortex/releases/download/v${CORTEX_VERSION}/cortex-cpp-${CORTEX_VERSION}-mac-arm64.tar.gz -o ./bin/ && mkdir -p ./bin/mac-arm64 && tar -zxvf ./bin/cortex-cpp-${CORTEX_VERSION}-mac-arm64.tar.gz --strip-components=1 -C ./bin/mac-arm64 && rm -rf ./bin/cortex-cpp-${CORTEX_VERSION}-mac-arm64.tar.gz && chmod +x ./bin/mac-arm64/cortex-cpp && download https://github.com/janhq/cortex/releases/download/v${CORTEX_VERSION}/cortex-cpp-${CORTEX_VERSION}-mac-amd64.tar.gz -o ./bin/ && mkdir -p ./bin/mac-amd64 && tar -zxvf ./bin/cortex-cpp-${CORTEX_VERSION}-mac-amd64.tar.gz --strip-components=1 -C ./bin/mac-amd64 && rm -rf ./bin/cortex-cpp-${CORTEX_VERSION}-mac-amd64.tar.gz && chmod +x ./bin/mac-amd64/cortex-cpp",
+    "downloadnitro:linux": "CORTEX_VERSION=$(cat ./bin/version.txt) && download https://github.com/janhq/cortex/releases/download/v${CORTEX_VERSION}/cortex-cpp-${CORTEX_VERSION}-linux-amd64.tar.gz -e --strip 1 -o ./bin/linux-cpu && chmod +x ./bin/linux-cpu/cortex-cpp && download https://github.com/janhq/cortex/releases/download/v${CORTEX_VERSION}/cortex-cpp-${CORTEX_VERSION}-linux-amd64.tar.gz -e --strip 1 -o ./bin/linux-cuda-12-0 && chmod +x ./bin/linux-cuda-12-0/cortex-cpp && download https://github.com/janhq/cortex/releases/download/v${CORTEX_VERSION}/cortex-cpp-${CORTEX_VERSION}-linux-amd64.tar.gz -e --strip 1 -o ./bin/linux-cuda-11-7 && chmod +x ./bin/linux-cuda-11-7/cortex-cpp && download https://github.com/janhq/cortex/releases/download/v${CORTEX_VERSION}/cortex-cpp-${CORTEX_VERSION}-linux-amd64.tar.gz -e --strip 1 -o ./bin/linux-vulkan && chmod +x ./bin/linux-vulkan/cortex-cpp && download https://github.com/janhq/cortex.llamacpp/releases/download/v0.1.25/cortex.llamacpp-0.1.25-linux-amd64-noavx.tar.gz -e --strip 1 -o ./bin/linux-cpu/engines/cortex.llamacpp && download https://github.com/janhq/cortex.llamacpp/releases/download/v0.1.25/cortex.llamacpp-0.1.25-linux-amd64-noavx-cuda-12-0.tar.gz -e --strip 1 -o ./bin/linux-cuda-12-0/engines/cortex.llamacpp && download https://github.com/janhq/cortex.llamacpp/releases/download/v0.1.25/cortex.llamacpp-0.1.25-linux-amd64-noavx-cuda-11-7.tar.gz -e --strip 1 -o ./bin/linux-cuda-11-7/engines/cortex.llamacpp && download https://github.com/janhq/cortex.llamacpp/releases/download/v0.1.25/cortex.llamacpp-0.1.25-linux-amd64-vulkan.tar.gz -e --strip 1 -o ./bin/linux-vulkan/engines/cortex.llamacpp",
+    "downloadnitro:darwin": "CORTEX_VERSION=$(cat ./bin/version.txt) && download https://github.com/janhq/cortex/releases/download/v${CORTEX_VERSION}/cortex-cpp-${CORTEX_VERSION}-mac-arm64.tar.gz -o ./bin/ && mkdir -p ./bin/mac-arm64 && tar -zxvf ./bin/cortex-cpp-${CORTEX_VERSION}-mac-arm64.tar.gz --strip-components=1 -C ./bin/mac-arm64 && rm -rf ./bin/cortex-cpp-${CORTEX_VERSION}-mac-arm64.tar.gz && chmod +x ./bin/mac-arm64/cortex-cpp && download https://github.com/janhq/cortex/releases/download/v${CORTEX_VERSION}/cortex-cpp-${CORTEX_VERSION}-mac-amd64.tar.gz -o ./bin/ && mkdir -p ./bin/mac-amd64 && tar -zxvf ./bin/cortex-cpp-${CORTEX_VERSION}-mac-amd64.tar.gz --strip-components=1 -C ./bin/mac-amd64 && rm -rf ./bin/cortex-cpp-${CORTEX_VERSION}-mac-amd64.tar.gz && chmod +x ./bin/mac-amd64/cortex-cpp && download https://github.com/janhq/cortex.llamacpp/releases/download/v0.1.25/cortex.llamacpp-0.1.25-mac-arm64.tar.gz -e --strip 1 -o ./bin/mac-arm64/engines/cortex.llamacpp && download https://github.com/janhq/cortex.llamacpp/releases/download/v0.1.25/cortex.llamacpp-0.1.25-mac-amd64.tar.gz -e --strip 1 -o ./bin/mac-amd64/engines/cortex.llamacpp",
     "downloadnitro:win32": "download.bat",
     "downloadnitro": "run-script-os",
     "build:publish:darwin": "rimraf *.tgz --glob && yarn build && npm run downloadnitro && ../../.github/scripts/auto-sign.sh && cpx \"bin/**\" \"dist/bin\" && npm pack && cpx *.tgz ../../pre-install",
diff --git a/extensions/inference-nitro-extension/src/node/index.ts b/extensions/inference-nitro-extension/src/node/index.ts
index 1b24e0a38..77ac9af7a 100644
--- a/extensions/inference-nitro-extension/src/node/index.ts
+++ b/extensions/inference-nitro-extension/src/node/index.ts
@@ -260,9 +260,14 @@ function loadLLMModel(settings: any): Promise<Response> {
 async function validateModelStatus(modelId: string): Promise<void> {
   // Send a GET request to the validation URL.
   // Retry the request up to 3 times if it fails, with a delay of 500 milliseconds between retries.
+  log(`[CORTEX]::Debug: Validating model ${modelId}`)
   return fetchRetry(NITRO_HTTP_VALIDATE_MODEL_URL, {
     method: 'POST',
-    body: JSON.stringify({ model: modelId }),
+    body: JSON.stringify({ 
+      model: modelId,
+      // TODO: force to use cortex llamacpp by default
+      engine: 'cortex.llamacpp'
+    }),
     headers: {
       'Content-Type': 'application/json',
     },
@@ -288,8 +293,9 @@ async function validateModelStatus(modelId: string): Promise<void> {
         return Promise.resolve()
       }
     }
+    const errorBody = await res.text()
     log(
-      `[CORTEX]::Debug: Validate model state failed with response ${JSON.stringify(
+      `[CORTEX]::Debug: Validate model state failed with response ${errorBody} and status is ${JSON.stringify(
         res.statusText
       )}`
     )