Public Access
55 lines
1.5 KiB
YAML
55 lines
1.5 KiB
YAML
model_list:
|
|
# --- TIER 1: OPENROUTER (3 Akun Load Balancing) ---
|
|
- model_name: primary
|
|
litellm_params:
|
|
model: openrouter/openai/gpt-4o-mini
|
|
api_key: os.environ/OPENROUTER_API_KEY_1
|
|
- model_name: primary
|
|
litellm_params:
|
|
model: openrouter/openai/gpt-4o-mini
|
|
api_key: os.environ/OPENROUTER_API_KEY_2
|
|
- model_name: primary
|
|
litellm_params:
|
|
model: openrouter/openai/gpt-4o-mini
|
|
api_key: os.environ/OPENROUTER_API_KEY_3
|
|
|
|
# --- TIER 2: GROQ (3 Akun Load Balancing) ---
|
|
- model_name: secondary
|
|
litellm_params:
|
|
model: groq/llama-3.3-70b-versatile
|
|
api_key: os.environ/GROQ_API_KEY_1
|
|
- model_name: secondary
|
|
litellm_params:
|
|
model: groq/llama-3.3-70b-versatile
|
|
api_key: os.environ/GROQ_API_KEY_2
|
|
- model_name: secondary
|
|
litellm_params:
|
|
model: groq/llama-3.3-70b-versatile
|
|
api_key: os.environ/GROQ_API_KEY_3
|
|
|
|
# --- TIER 3: GITHUB MODELS (3 Akun) ---
|
|
- model_name: tertiary
|
|
litellm_params:
|
|
model: github/gpt-4o-mini
|
|
api_key: os.environ/GITHUB_TOKEN_1
|
|
- model_name: tertiary
|
|
litellm_params:
|
|
model: github/gpt-4o-mini
|
|
api_key: os.environ/GITHUB_TOKEN_2
|
|
- model_name: tertiary
|
|
litellm_params:
|
|
model: github/gpt-4o-mini
|
|
api_key: os.environ/GITHUB_TOKEN_3
|
|
|
|
router_settings:
|
|
routing_strategy: simple-shuffle
|
|
fallbacks:
|
|
primary:
|
|
- secondary
|
|
- tertiary
|
|
retry_after: 0
|
|
num_retries: 2
|
|
timeout: 60
|
|
allowed_fails: 3 # per akun — jadi tiap akun boleh fail 3x sebelum cooldown
|
|
cooldown_time: 60
|