diff --git a/routes/model_routes.py b/routes/model_routes.py
index 864035884..b88fa3ef1 100644
--- a/routes/model_routes.py
+++ b/routes/model_routes.py
@@ -283,6 +283,7 @@ _HOST_TO_CURATED = (
     ("fireworks.ai", "fireworks"),
     ("googleapis.com", "google"),
     ("x.ai", "xai"),
+    ("nvidia.com", "nvidia"),
     ("openrouter.ai", "openrouter"),
     ("ollama.com", "ollama"),
 )
@@ -477,10 +478,17 @@ _NON_CHAT_PREFIXES = (
     "dall-e", "tts-", "whisper", "text-embedding", "embedding",
     "davinci", "babbage", "moderation", "omni-moderation",
     "sora", "gpt-image", "chatgpt-image",
+    # embedding / retrieval / non-chat models (common across providers)
+    "snowflake/arctic-embed", "nvidia/nv-embed", "embed",
 )
 _NON_CHAT_CONTAINS = (
     "-realtime", "-transcribe", "-tts", "-codex",
-    "codex-",
+    "codex-", "content-safety", "-safety", "-reward", "nvclip",
+    "kosmos", "fuyu", "deplot", "vila", "neva",
+    "gliner", "riva", "-parse", "-embedqa", "-nemoretriever",
+    "topic-control", "calibration",
+    "ai-synthetic-video", "cosmos-reason2",
+    "bge", "llama-guard",
 )
 _NON_CHAT_EXACT_PREFIXES = (
     "gpt-audio",  # gpt-audio, gpt-audio-mini etc. (not gpt-4o-audio-preview which is chat)
@@ -731,7 +739,7 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
                 for _e in _PROVIDER_CURATED.get(_ck, []):
                     if _e not in set(models) and not any(m.startswith(_e) for m in models):
                         models.append(_e)
-            return models
+            return [m for m in models if _is_chat_model(m)]
     except httpx.HTTPStatusError as e:
         if api_key:
             status = e.response.status_code if e.response is not None else "unknown"
@@ -755,7 +763,7 @@ def _probe_endpoint(base_url: str, api_key: str = None, timeout: int = 5) -> Lis
             data = r.json()
             models = [m.get("name") or m.get("model") for m in (data.get("models") or []) if m.get("name") or m.get("model")]
             if models:
-                return models
+                return [m for m in models if _is_chat_model(m)]
     except Exception as e:
         logger.debug(f"Ollama /api/tags probe failed for {base}: {e}")
     # Fall back to curated list if the provider has a URL-based match (e.g. z.ai has no /models endpoint)
diff --git a/src/llm_core.py b/src/llm_core.py
index 07b149ebe..b012638fa 100644
--- a/src/llm_core.py
+++ b/src/llm_core.py
@@ -444,6 +444,8 @@ def _detect_provider(url: str) -> str:
         return "openrouter"
     if _host_match(url, "groq.com"):
         return "groq"
+    if _host_match(url, "nvidia.com"):
+        return "nvidia"
     from src.chatgpt_subscription import is_chatgpt_subscription_base
     if is_chatgpt_subscription_base(url):
         return "chatgpt-subscription"
@@ -489,6 +491,7 @@ def _provider_label(url: str) -> str:
     if is_copilot_base(url): return "GitHub Copilot"
     if _host_match(url, "mistral.ai"): return "Mistral"
     if _host_match(url, "deepseek.com"): return "DeepSeek"
+    if _host_match(url, "nvidia.com"): return "NVIDIA"
     if _host_match(url, "googleapis.com"): return "Google"
     if _host_match(url, "together.xyz", "together.ai"): return "Together"
     if _host_match(url, "fireworks.ai"): return "Fireworks"
diff --git a/static/index.html b/static/index.html
index 4ca33c072..60a2764d9 100644
--- a/static/index.html
+++ b/static/index.html
@@ -2095,6 +2095,7 @@
                   <option value="https://opencode.ai/zen/v1" data-logo="opencode">OpenCode Zen</option>
                   <option value="https://opencode.ai/zen/go/v1" data-logo="opencode">OpenCode Go</option>
                   <option value="https://api.z.ai/api/coding/paas/v4" data-logo="zhipu">Z.AI Coding Plan</option>
+                  <option value="https://integrate.api.nvidia.com/v1" data-logo="nvidia">NVIDIA</option>
                 </select>
                 <!-- API key row stays in DOM, hidden until Key button is
                      clicked. Mirrors the Local section pattern: most users
diff --git a/static/js/providers.js b/static/js/providers.js
index 1c9c5080a..f42afcd67 100644
--- a/static/js/providers.js
+++ b/static/js/providers.js
@@ -118,6 +118,7 @@ const _ENDPOINT_LABELS = [
   [/(^|\.)together\.(ai|xyz)$/i, "Together"],
   [/(^|\.)fireworks\.ai$/i, "Fireworks"],
   [/(^|\.)perplexity\.ai$/i, "Perplexity"],
+  [/(^|\.)nvidia\.com$/i, "NVIDIA"],
   [/(^|\.)x\.ai$/i, "xAI"],
 ];
 
diff --git a/static/js/slashCommands.js b/static/js/slashCommands.js
index 28b1a08e4..6a32cb89e 100644
--- a/static/js/slashCommands.js
+++ b/static/js/slashCommands.js
@@ -43,6 +43,7 @@ const PROVIDER_PATTERNS = [
   { re: /^gsk_/,             name: 'Groq',       url: 'https://api.groq.com/openai/v1' },
   { re: /^AIza/,             name: 'Gemini',     url: 'https://generativelanguage.googleapis.com/v1beta/openai' },
   { re: /^xai-/,             name: 'xAI',        url: 'https://api.x.ai/v1' },
+  { re: /^nvapi-/,           name: 'NVIDIA',     url: 'https://integrate.api.nvidia.com/v1' },
 ];
 const SETUP_PROVIDER_URLS = {
   deepseek: { name: 'DeepSeek', url: 'https://api.deepseek.com/v1' },
@@ -56,8 +57,9 @@ const SETUP_PROVIDER_URLS = {
   google: { name: 'Gemini', url: 'https://generativelanguage.googleapis.com/v1beta/openai' },
   'opencode-zen': { name: 'OpenCode Zen', url: 'https://opencode.ai/zen/v1' },
   'opencode-go': { name: 'OpenCode Go', url: 'https://opencode.ai/zen/go/v1' },
+  nvidia: { name: 'NVIDIA', url: 'https://integrate.api.nvidia.com/v1' },
 };
-const SETUP_PROVIDER_NAMES = ['deepseek', 'openai', 'openrouter', 'ollama', 'xai', 'anthropic', 'groq', 'gemini', 'opencode-zen', 'opencode-go'];
+const SETUP_PROVIDER_NAMES = ['deepseek', 'openai', 'openrouter', 'ollama', 'xai', 'anthropic', 'groq', 'gemini', 'opencode-zen', 'opencode-go', 'nvidia'];
 const SETUP_DEVICE_AUTH_PROVIDERS = [
   { key: 'copilot', name: 'GitHub Copilot', aliases: ['github'], command: '/setup copilot' },
   { key: 'chatgpt-subscription', name: 'ChatGPT Subscription', aliases: ['chatgptsubscription', 'chatgpt-sub', 'codex'], command: '/setup chatgpt-subscription' },
@@ -97,6 +99,7 @@ function _setupProviderFromInput(input) {
     google: 'gemini',
     xai: 'xai',
     grok: 'xai',
+    nvidia: 'nvidia',
   };
   return SETUP_PROVIDER_URLS[aliases[raw] || raw] || null;
 }
@@ -124,6 +127,7 @@ function _extractSetupProviderCredential(input) {
     ['groq', 'groq'],
     ['google', 'gemini'], ['gemini', 'gemini'],
     ['x ai', 'xai'], ['xai', 'xai'], ['grok', 'xai'],
+    ['nvidia', 'nvidia'],
   ];
   for (const [alias, key] of providerAliases) {
     const re = new RegExp('(^|\\s|[,;:])(' + alias.replace(/\s+/g, '\\s+') + ')(?=$|\\s|[,;:])', 'i');
diff --git a/tests/test_model_routes.py b/tests/test_model_routes.py
index 02f2ea071..3b23123ef 100644
--- a/tests/test_model_routes.py
+++ b/tests/test_model_routes.py
@@ -347,6 +347,8 @@ class TestIsChatModel:
         "gpt-4o", "gpt-4o-mini", "claude-sonnet-4", "llama-3.3-70b",
         "deepseek-chat", "gemini-2.0-flash", "o3",
         "llama-4-scout-17b-16e-instruct",
+        "gemma-2b-it", "google/gemma-2b-it",
+        "bigcode/starcoder2-15b-instruct",
     ])
     def test_chat_models(self, model_id):
         assert _is_chat_model(model_id) is True
diff --git a/tests/test_provider_classification.py b/tests/test_provider_classification.py
index 43fd0a0df..48d413dcb 100644
--- a/tests/test_provider_classification.py
+++ b/tests/test_provider_classification.py
@@ -40,6 +40,7 @@ class TestDetectProvider:
         ("https://anthropic.com/v1", "anthropic"),
         ("https://openrouter.ai/api/v1", "openrouter"),
         ("https://api.groq.com/openai/v1", "groq"),
+        ("https://integrate.api.nvidia.com/v1", "nvidia"),
         ("http://localhost:11434/api", "ollama"),
         ("https://ollama.com", "ollama"),
         # xAI, DeepSeek and Gemini's OpenAI-compatible surface are NOT
@@ -84,6 +85,7 @@ class TestProviderLabel:
         ("https://api.openai.com/v1", "OpenAI"),
         ("https://openrouter.ai/api/v1", "OpenRouter"),
         ("https://api.groq.com/openai/v1", "Groq"),
+        ("https://integrate.api.nvidia.com/v1", "NVIDIA"),
         ("https://api.mistral.ai/v1", "Mistral"),
         ("https://api.deepseek.com", "DeepSeek"),
         ("https://generativelanguage.googleapis.com/v1beta/openai", "Google"),
diff --git a/tests/test_provider_endpoints.py b/tests/test_provider_endpoints.py
index 6c271557e..d4b56dcb3 100644
--- a/tests/test_provider_endpoints.py
+++ b/tests/test_provider_endpoints.py
@@ -50,6 +50,9 @@ PROVIDER_CASES = [
     ("groq", "https://api.groq.com/openai/v1",
      "https://api.groq.com/openai/v1/chat/completions",
      "https://api.groq.com/openai/v1/models"),
+    ("nvidia", "https://integrate.api.nvidia.com/v1",
+     "https://integrate.api.nvidia.com/v1/chat/completions",
+     "https://integrate.api.nvidia.com/v1/models"),
     ("xai", "https://api.x.ai/v1",
      "https://api.x.ai/v1/chat/completions",
      "https://api.x.ai/v1/models"),
@@ -112,6 +115,7 @@ def test_headers_anthropic_without_key_still_sends_version():
     "https://api.x.ai/v1",
     "https://api.deepseek.com",
     "https://api.groq.com/openai/v1",
+    "https://integrate.api.nvidia.com/v1",
     "https://generativelanguage.googleapis.com/v1beta/openai",
 ])
 def test_headers_openai_style_use_bearer(base):