mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-26 01:12:21 +00:00
c8e0f2ddb4
Shipped proxy configs now read general_settings.master_key from os.environ/LITELLM_MASTER_KEY, the .env examples ship a blank value with the openssl generate command above it, and READMEs, the missing env vars page and Admin UI code snippets show a generate command or the <your-master-key> placeholder instead of the literal sk-1234 The two CircleCI docker runs that mount proxy_server_config.yaml and oai_misc_config.yaml now pass LITELLM_MASTER_KEY so their runtime key is unchanged
83 lines
2.8 KiB
YAML
83 lines
2.8 KiB
YAML
# model_list:
|
|
# - model_name: claude-sonnet-4-6
|
|
# litellm_params: {model: anthropic/claude-sonnet-4-6}
|
|
# model_info:
|
|
# litellm_routing_preferences:
|
|
# quality_tier: 1
|
|
# keywords: [tin]
|
|
# - model_name: gpt-4o-mini
|
|
# litellm_params: {model: openai/gpt-4o-mini}
|
|
# model_info:
|
|
# litellm_routing_preferences:
|
|
# quality_tier: 1
|
|
# keywords: []
|
|
# - model_name: gpt-4o
|
|
# litellm_params: {model: openai/gpt-4o}
|
|
# model_info:
|
|
# litellm_routing_preferences:
|
|
# quality_tier: 2
|
|
# keywords: [vision, function_calling]
|
|
# - model_name: opus
|
|
# litellm_params: {model: anthropic/claude-opus-4-7}
|
|
# model_info:
|
|
# litellm_routing_preferences:
|
|
# quality_tier: 3
|
|
# keywords: ["architecture", "design"]
|
|
# - model_name: my-quality-router
|
|
# litellm_params:
|
|
# model: auto_router/adaptive_router
|
|
# adaptive_router_default_model: gpt-4o-mini
|
|
# adaptive_router_config:
|
|
# available_models: [gpt-4o-mini, gpt-4o, opus, claude-sonnet-4-6]
|
|
# Example proxy config for the adaptive router (v0).
|
|
#
|
|
# Wires one logical router ("smart-cheap-router") that adaptively picks between
|
|
# two real deployments ("fast" and "smart") based on per-session feedback signals.
|
|
#
|
|
# How to use from a client:
|
|
# POST /v1/chat/completions { "model": "smart-cheap-router", ... }
|
|
# Add { "metadata": { "litellm_session_id": "<your-session-id>" } } to enable
|
|
# sticky-session routing within a conversation.
|
|
#
|
|
# Required env vars: OPENAI_API_KEY, DATABASE_URL.
|
|
|
|
model_list:
|
|
# ---- The adaptive router "control" deployment -------------------------
|
|
# `model_name` is what clients call. `available_models` lists the underlying
|
|
# deployments the router is allowed to pick from (must match other model_name
|
|
# entries in this list).
|
|
- model_name: smart-cheap-router
|
|
litellm_params:
|
|
model: auto_router/adaptive_router
|
|
adaptive_router_config:
|
|
available_models: ["fast", "smart"]
|
|
weights:
|
|
quality: 0.7
|
|
cost: 0.3
|
|
|
|
# ---- Underlying deployments the router picks from ---------------------
|
|
- model_name: fast
|
|
litellm_params:
|
|
model: anthropic/claude-sonnet-4-6
|
|
api_key: os.environ/ANTHROPIC_API_KEY
|
|
input_cost_per_token: 0.00000015
|
|
model_info:
|
|
adaptive_router_preferences:
|
|
quality_tier: 2
|
|
strengths: []
|
|
|
|
- model_name: smart
|
|
litellm_params:
|
|
model: anthropic/claude-opus-4-7
|
|
api_key: os.environ/ANTHROPIC_API_KEY
|
|
input_cost_per_token: 0.0000050
|
|
model_info:
|
|
adaptive_router_preferences:
|
|
quality_tier: 3
|
|
strengths: ["code_generation", "technical_design", "analytical_reasoning"]
|
|
|
|
litellm_settings:
|
|
drop_params: True
|
|
|
|
general_settings:
|
|
master_key: os.environ/LITELLM_MASTER_KEY
|