diff --git a/docs_new/cookbook/autoregressive/DeepSeek/DeepSeek-V4.mdx b/docs_new/cookbook/autoregressive/DeepSeek/DeepSeek-V4.mdx
index 9d857e233..e11b3a75a 100644
--- a/docs_new/cookbook/autoregressive/DeepSeek/DeepSeek-V4.mdx
+++ b/docs_new/cookbook/autoregressive/DeepSeek/DeepSeek-V4.mdx
@@ -80,6 +80,10 @@ Please refer to the [official SGLang installation guide](../../../docs/get-start
     </tr>
   </thead>
   <tbody>
+    <tr>
+      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>NVIDIA B300</td>
+      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>lmsysorg/sglang:deepseek-v4-b300</code></td>
+    </tr>
     <tr>
       <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>NVIDIA B200</td>
       <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}><code>lmsysorg/sglang:deepseek-v4-blackwell</code></td>
diff --git a/docs_new/src/snippets/autoregressive/deepseek-v4-deployment.jsx b/docs_new/src/snippets/autoregressive/deepseek-v4-deployment.jsx
index 50d53732d..5943d4568 100644
--- a/docs_new/src/snippets/autoregressive/deepseek-v4-deployment.jsx
+++ b/docs_new/src/snippets/autoregressive/deepseek-v4-deployment.jsx
@@ -26,6 +26,7 @@ export const DeepSeekV4Deployment = () => {
       title: "Hardware Platform",
       items: [
         { id: "b200",  label: "B200 (FP4)",  default: true  },
+        { id: "b300",  label: "B300 (FP4)",  default: false  },
         { id: "gb300", label: "GB300 (FP4)", default: false },
         { id: "h200",  label: "H200 (FP8)",  default: false },
       ],
@@ -222,7 +223,9 @@ export const DeepSeekV4Deployment = () => {
   // === SHARED END ===
 
   const generateCommand = () => {
-    const { hardware, modelSize, recipe, reasoningParser, toolcall } = values;
+    const { hardware: rawHardware, modelSize, recipe, reasoningParser, toolcall } = values;
+    // B300 usage is identical to B200 — alias so we don't duplicate every spec entry.
+    const hardware = rawHardware === "b300" ? "b200" : rawHardware;
     const specKey = `${hardware}|${modelSize}`;
     const spec = HW_SIZE_SPEC[specKey];
     const { slug, tp, multinode, nnodes } = spec;
@@ -439,7 +442,9 @@ export const DeepSeekV4Deployment = () => {
   //   --max-running-requests 256 only on decode (PD decode can't retract).
   //   No flashinfer_mxfp4 / autotune-fix / MTP / mem-fraction-static on PD (allinone omits).
   // ============================================================================
-  const buildPDDisaggCommand = (hardware, modelSize) => {
+  const buildPDDisaggCommand = (rawHardware, modelSize) => {
+    // B300 usage is identical to B200 — alias so we don't duplicate every spec entry.
+    const hardware = rawHardware === "b300" ? "b200" : rawHardware;
     const specKey = `${hardware}|${modelSize}`;
     const { tp: pdTp, multinode, nnodes } = PD_TP_SPEC[specKey];
     const slug = HW_SIZE_SPEC[specKey].slug;