From 6e0178655b94813762534b7642ba5174b45f022e Mon Sep 17 00:00:00 2001
From: Annie Surla <110621965+anniesurla@users.noreply.github.com>
Date: Sun, 19 Apr 2026 17:57:49 -0700
Subject: [PATCH] feat(provider): add NVIDIA to popular providers, docs, and
 attribution headers (#22927)

Co-authored-by: Kit Langton <kit.langton@gmail.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
---
 packages/opencode/src/provider/provider.ts  | 10 ++++
 packages/web/src/content/docs/providers.mdx | 61 +++++++++++++++------
 2 files changed, 54 insertions(+), 17 deletions(-)

diff --git a/packages/opencode/src/provider/provider.ts b/packages/opencode/src/provider/provider.ts
index 8f6e1556ad..6e116fe41e 100644
--- a/packages/opencode/src/provider/provider.ts
+++ b/packages/opencode/src/provider/provider.ts
@@ -410,6 +410,16 @@ function custom(dep: CustomDep): Record<string, CustomLoader> {
           },
         },
       }),
+    nvidia: () =>
+      Effect.succeed({
+        autoload: false,
+        options: {
+          headers: {
+            "HTTP-Referer": "https://opencode.ai/",
+            "X-Title": "opencode",
+          },
+        },
+      }),
     vercel: () =>
       Effect.succeed({
         autoload: false,
diff --git a/packages/web/src/content/docs/providers.mdx b/packages/web/src/content/docs/providers.mdx
index bad9e1ebbc..030a50ba00 100644
--- a/packages/web/src/content/docs/providers.mdx
+++ b/packages/web/src/content/docs/providers.mdx
@@ -1316,30 +1316,57 @@ To use Kimi K2 from Moonshot AI:
 
 ---
 
-### Mistral AI
+### NVIDIA
 
-1.  Head over to the [Mistral AI console](https://console.mistral.ai/), create an account, and generate an API key.
+NVIDIA provides access to Nemotron models and many other open models through [build.nvidia.com](https://build.nvidia.com) for free.
 
-2.  Run the `/connect` command and search for **Mistral AI**.
+1. Head over to [build.nvidia.com](https://build.nvidia.com), create an account, and generate an API key.
 
-    ```txt
-    /connect
-    ```
+2. Run the `/connect` command and search for **NVIDIA**.
 
-3.  Enter your Mistral API key.
+   ```txt
+   /connect
+   ```
 
-    ```txt
-    ┌ API key
-    │
-    │
-    └ enter
-    ```
+3. Enter your NVIDIA API key.
 
-4.  Run the `/models` command to select a model like _Mistral Medium_.
+   ```txt
+   ┌ API key
+   │
+   │
+   └ enter
+   ```
 
-    ```txt
-    /models
-    ```
+4. Run the `/models` command to select a model like nemotron-3-super-120b-a12b.
+
+   ```txt
+   /models
+   ```
+
+#### On-Prem / NIM
+
+You can also use NVIDIA models locally via [NVIDIA NIM](https://docs.nvidia.com/nim/) by setting a custom base URL.
+
+```json title="opencode.json" {6}
+{
+  "$schema": "https://opencode.ai/config.json",
+  "provider": {
+    "nvidia": {
+      "options": {
+        "baseURL": "http://localhost:8000/v1"
+      }
+    }
+  }
+}
+```
+
+#### Environment Variable
+
+Alternatively, set your API key as an environment variable.
+
+```bash frame="none"
+export NVIDIA_API_KEY=nvapi-your-key-here
+```
 
 ---