Config baru: groq, openrouter, github doang (3 tier)

.env.example

@@ -1,30 +1,14 @@
 # AI PROXY CONFIG
 # Copy file ini ke .env dan isi API key masing-masing
 
-# Gemini (Tier 1 - main)
+# OpenRouter (Tier 1)
-GEMINI_API_KEY_1=
-GEMINI_API_KEY_2=
-GEMINI_API_KEY_3=
-GEMINI_API_KEY_4=
-GEMINI_API_KEY_5=
-
-# GitHub Models (Tier 2 - fallback)
-GITHUB_TOKEN_1=
-GITHUB_TOKEN_2=
-
-# Groq (Tier 3 - emergency)
-GROQ_API_KEY_1=
-GROQ_API_KEY_2=
-
-# OpenRouter (free tier)
 OPENROUTER_API_KEY_1=
-OPENROUTER_API_KEY_2=
-OPENROUTER_API_KEY_3=
 
-# Others
+# Groq (Tier 2)
-DEEPSEEK_API_KEY=
+GROQ_API_KEY_1=
-TOGETHER_API_KEY=
+
-HUGGINGFACE_API_KEY=
+# GitHub Models (Tier 3)
+GITHUB_TOKEN_1=
 
 # LiteLLM Admin
 LITELLM_MASTER_KEY=

README.md

@@ -60,9 +60,9 @@ curl http://localhost:4000/v1/chat/completions \
 
 | Tier | Model Name | Provider | Akun | Fungsi |
 |------|-----------|----------|------|--------|
-| 1 | `hermes-engine` | Gemini 2.5 Flash | 5 | Main — load balanced otomatis |
+| 1 | `primary` | GPT-4o Mini (OpenRouter) | 1 | Main |
-| 2 | `tier2-fallback` | GPT-4o Mini (GitHub) | 2 | Cadangan kalo Gemini error semua |
+| 2 | `secondary` | Llama 3.3 70B (Groq) | 1 | Fallback pertama |
-| 3 | `tier3-emergency` | Llama 3 70B (Groq) | 2 | Darurat kalo semua tier error |
+| 3 | `tertiary` | GPT-4o Mini (GitHub) | 1 | Fallback terakhir |
 
 ## Port
 

config.yaml

@@ -1,59 +1,30 @@
 model_list:
-  # --- TIER 1: GEMINI (5 Akun Load Balancing) ---
+  # --- TIER 1: OPENROUTER (Free) ---
-  - model_name: hermes-engine
+  - model_name: primary
     litellm_params:
-      model: gemini/gemini-2.5-flash
+      model: openrouter/openai/gpt-4o-mini
-      api_key: os.environ/GEMINI_API_KEY_1
+      api_key: os.environ/OPENROUTER_API_KEY_1
-      tpm_fallback: true
-  - model_name: hermes-engine
-    litellm_params:
-      model: gemini/gemini-2.5-flash
-      api_key: os.environ/GEMINI_API_KEY_2
-      tpm_fallback: true
-  - model_name: hermes-engine
-    litellm_params:
-      model: gemini/gemini-2.5-flash
-      api_key: os.environ/GEMINI_API_KEY_3
-      tpm_fallback: true
-  - model_name: hermes-engine
-    litellm_params:
-      model: gemini/gemini-2.5-flash
-      api_key: os.environ/GEMINI_API_KEY_4
-      tpm_fallback: true
-  - model_name: hermes-engine
-    litellm_params:
-      model: gemini/gemini-2.5-flash
-      api_key: os.environ/GEMINI_API_KEY_5
-      tpm_fallback: true
 
-  # --- TIER 2: GITHUB MODELS (2 Akun Cadangan) ---
+  # --- TIER 2: GROQ (Free) ---
-  - model_name: tier2-fallback
+  - model_name: secondary
+    litellm_params:
+      model: groq/llama-3.3-70b-versatile
+      api_key: os.environ/GROQ_API_KEY_1
+
+  # --- TIER 3: GITHUB MODELS (via token) ---
+  - model_name: tertiary
     litellm_params:
       model: github/gpt-4o-mini
       api_key: os.environ/GITHUB_TOKEN_1
-  - model_name: tier2-fallback
-    litellm_params:
-      model: github/gpt-4o-mini
-      api_key: os.environ/GITHUB_TOKEN_2
-
-  # --- TIER 3: GROQ (2 Akun Darurat) ---
-  - model_name: tier3-emergency
-    litellm_params:
-      model: groq/llama3-70b-8192
-      api_key: os.environ/GROQ_API_KEY_1
-  - model_name: tier3-emergency
-    litellm_params:
-      model: groq/llama3-70b-8192
-      api_key: os.environ/GROQ_API_KEY_2
 
 router_settings:
   routing_strategy: simple-shuffle
   fallbacks:
-    - hermes-engine:
+    primary:
-        - tier2-fallback
+      - secondary
-        - tier3-emergency
+      - tertiary
   retry_after: 0
   num_retries: 2
   timeout: 60
-  allowed_fails: 1
+  allowed_fails: 2
   cooldown_time: 60