feat: Add 3 new FREE models - Mistral Medium 3, GPT-4o-mini (GitHub), TinyLlama 1.1B

TIER 2: FREE GITHUB MODELS
- Mistral Medium 3 (GitHub) 🆓: Advanced reasoning + vision (131K context)
- GPT-4o-mini (GitHub) 🆓: Fast GPT-4o-mini (128K context)

TIER 5: FREE HUGGINGFACE MODELS
- TinyLlama 1.1B 🤗: Ultra-fast 1.1B model for simple tasks (2K context)

Total models: 11 (was 8)
All use FREE APIs with appropriate tokens

app.py

@@ -35,7 +35,28 @@ MODEL_CONFIGS = {
         "description": "Best for general purpose"
     },
 
-    # === TIER 2: FREE GROQ MODELS ===
+
+    # === TIER 2: FREE GITHUB MODELS ===
+    "Mistral Medium 3 (GitHub) 🆓": {
+        "provider": "github",
+        "model": "Mistral-Medium-3",
+        "api_key_env": "GITHUB_TOKEN",
+        "cost_per_1M_tokens": 0.00,
+        "context_window": 131072,
+        "tier": "free-github",
+        "description": "Advanced reasoning + vision via GitHub Models (FREE)"
+    },
+    "GPT-4o-mini (GitHub) 🆓": {
+        "provider": "github",
+        "model": "gpt-4o-mini",
+        "api_key_env": "GITHUB_TOKEN",
+        "cost_per_1M_tokens": 0.00,
+        "context_window": 128000,
+        "tier": "free-github",
+        "description": "Fast GPT-4o-mini via GitHub Models (FREE)"
+    },
+
+    # === TIER 3: FREE GROQ MODELS ===
     "Llama 3.3 70B (Groq) 🚀": {
         "provider": "groq",
         "model": "llama-3.3-70b-versatile",
@@ -94,6 +115,15 @@ MODEL_CONFIGS = {
         "context_window": 16384,
         "tier": "free-hf",
         "description": "Microsoft's efficient code model via HF Inference API"
+    },
+    "TinyLlama 1.1B 🤗": {
+        "provider": "huggingface",
+        "model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+        "api_key_env": "HF_TOKEN",
+        "cost_per_1M_tokens": 0.00,
+        "context_window": 2048,
+        "tier": "free-hf",
+        "description": "Ultra-fast 1.1B model for simple tasks (FREE)"
     }
 }