Add NVIDIA NIM provider (DeepSeek V4 Pro, GLM) — free tier

scripts/llm_solver_cloud.py

@@ -3,26 +3,29 @@ PEMF ARC-AGI — LLM Program Synthesis (Multi-Provider)
 =====================================================
 
 Supports:
-  - Google Gemini (free tier: 15 RPM, generous limits)
-  - DeepSeek V4 (very cheap: $0.07/M input tokens)  
-  - GLM-4 / ChatGLM (free tier available)
+  - NVIDIA NIM (free — DeepSeek V4 Pro, GLM-4, Qwen, Llama)
+  - Google Gemini (free tier: 15 RPM)
+  - DeepSeek direct API (very cheap)
+  - GLM/Zhipu direct API (free tier)
   - Ollama local (any model)
-  - Any OpenAI-compatible API
 
 Usage:
-  # Gemini (free, recommended starting point)
-  export LLM_PROVIDER=gemini
-  export GEMINI_API_KEY=your_key_here
+  # NVIDIA NIM — FREE, best option (DeepSeek V4 Pro)
+  export LLM_PROVIDER=nvidia
+  export NVIDIA_API_KEY=nvapi-xxxxx
   python llm_solver_cloud.py
+  # Get key: https://build.nvidia.com/settings/api-keys
+  # Models: deepseek-ai/deepseek-v4-pro, thudm/glm-4-9b-chat, etc.
 
-  # DeepSeek (cheapest cloud option)
-  export LLM_PROVIDER=deepseek
-  export DEEPSEEK_API_KEY=your_key_here
+  # NVIDIA NIM with GLM
+  export LLM_PROVIDER=nvidia
+  export NVIDIA_API_KEY=nvapi-xxxxx
+  export LLM_MODEL=thudm/glm-4-9b-chat
   python llm_solver_cloud.py
 
-  # GLM
-  export LLM_PROVIDER=glm
-  export GLM_API_KEY=your_key_here
+  # Gemini (free)
+  export LLM_PROVIDER=gemini
+  export GEMINI_API_KEY=your_key
   python llm_solver_cloud.py
 
   # Ollama local
@@ -48,6 +51,14 @@ import urllib.request
 # =============================================================================
 
 PROVIDERS = {
+    "nvidia": {
+        "name": "NVIDIA NIM (free tier — DeepSeek V4, GLM, Qwen, Llama)",
+        "base_url": "https://integrate.api.nvidia.com/v1/chat/completions",
+        "default_model": "deepseek-ai/deepseek-v4-pro",
+        "env_key": "NVIDIA_API_KEY",
+        "free_tier": "Free for NVIDIA Developer Program members (1000 credits)",
+        "get_key_url": "https://build.nvidia.com/settings/api-keys",
+    },
     "gemini": {
         "name": "Google Gemini",
         "base_url": "https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent",
@@ -57,7 +68,7 @@ PROVIDERS = {
         "get_key_url": "https://aistudio.google.com/apikey",
     },
     "deepseek": {
-        "name": "DeepSeek",
+        "name": "DeepSeek (direct API)",
         "base_url": "https://api.deepseek.com/v1/chat/completions",
         "default_model": "deepseek-chat",
         "env_key": "DEEPSEEK_API_KEY",
@@ -65,7 +76,7 @@ PROVIDERS = {
         "get_key_url": "https://platform.deepseek.com/api_keys",
     },
     "glm": {
-        "name": "GLM (Zhipu AI)",
+        "name": "GLM (Zhipu AI direct)",
         "base_url": "https://open.bigmodel.cn/api/paas/v4/chat/completions",
         "default_model": "glm-4-flash",
         "env_key": "GLM_API_KEY",
@@ -85,6 +96,29 @@ PROVIDERS = {
 # API CALLERS
 # =============================================================================
 
+def call_nvidia(prompt: str, api_key: str, model: str = "deepseek-ai/deepseek-v4-pro",
+                temperature: float = 0.7) -> str:
+    """Call NVIDIA NIM API (OpenAI-compatible). Hosts DeepSeek V4, GLM, Qwen, Llama."""
+    url = "https://integrate.api.nvidia.com/v1/chat/completions"
+    payload = {
+        "model": model,
+        "messages": [{"role": "user", "content": prompt}],
+        "max_tokens": 2048,
+        "temperature": temperature,
+    }
+    data = json.dumps(payload).encode('utf-8')
+    req = urllib.request.Request(url, data=data,
+                                headers={"Content-Type": "application/json",
+                                         "Authorization": f"Bearer {api_key}"},
+                                method='POST')
+    try:
+        with urllib.request.urlopen(req, timeout=120) as resp:
+            result = json.loads(resp.read().decode())
+            return result['choices'][0]['message']['content']
+    except Exception as e:
+        return f"ERROR: {e}"
+
+
 def call_gemini(prompt: str, api_key: str, model: str = "gemini-2.0-flash",
                 temperature: float = 0.7) -> str:
     """Call Google Gemini API."""
@@ -184,7 +218,9 @@ def call_ollama(prompt: str, model: str = "qwen2.5-coder:32b",
 def call_llm(prompt: str, provider: str, api_key: str = "",
              model: str = "", temperature: float = 0.7) -> str:
     """Unified LLM caller."""
-    if provider == "gemini":
+    if provider == "nvidia":
+        return call_nvidia(prompt, api_key, model or "deepseek-ai/deepseek-v4-pro", temperature)
+    elif provider == "gemini":
         return call_gemini(prompt, api_key, model or "gemini-2.0-flash", temperature)
     elif provider == "deepseek":
         return call_deepseek(prompt, api_key, model or "deepseek-chat", temperature)
@@ -402,6 +438,8 @@ def main():
         # Rate limit respect
         if PROVIDER == "gemini":
             time.sleep(4)  # 15 RPM = 1 every 4s
+        elif PROVIDER == "nvidia":
+            time.sleep(2)  # NIM free tier: ~30 RPM
         elif PROVIDER in ("deepseek", "glm"):
             time.sleep(1)