83d516afa1
FastAPI gateway with A/B/C lane orchestration, LiteLLM proxy config, Swarm stack (postgres, redis, VPN off-by-default), deploy/smoke/audit scripts.
106 lines
2.5 KiB
YAML
106 lines
2.5 KiB
YAML
# tier × lane (A/B/C) → Novita model id + LiteLLM fallbacks
|
||
|
||
lanes:
|
||
A: economy
|
||
B: balanced
|
||
C: max
|
||
|
||
models:
|
||
a-simple:
|
||
novita: novita/qwen/qwen3-4b-fp8
|
||
fallbacks: [b-simple, groq-llama-8b]
|
||
rpm: 60
|
||
b-simple:
|
||
novita: novita/meta-llama/llama-3.1-8b-instruct
|
||
fallbacks: [a-simple, groq-llama-8b]
|
||
rpm: 60
|
||
c-simple:
|
||
novita: novita/qwen/qwen3-8b-fp8
|
||
fallbacks: [b-simple]
|
||
rpm: 60
|
||
|
||
a-medium-ops:
|
||
novita: novita/qwen/qwen3-8b-fp8
|
||
fallbacks: [a-medium-code, b-medium-ops]
|
||
rpm: 40
|
||
b-medium-ops:
|
||
novita: novita/deepseek/deepseek-v3.2
|
||
fallbacks: [a-medium-code, c-medium-ops]
|
||
rpm: 40
|
||
c-medium-ops:
|
||
novita: novita/deepseek/deepseek-v3.2
|
||
fallbacks: [b-medium-ops]
|
||
rpm: 40
|
||
|
||
a-medium-code:
|
||
novita: novita/qwen/qwen3-coder-30b-a3b-instruct
|
||
fallbacks: [a-medium-ops, groq-qwen-coder]
|
||
rpm: 40
|
||
b-medium-code:
|
||
novita: novita/qwen/qwen3-coder-30b-a3b-instruct
|
||
fallbacks: [b-medium-ops, c-medium-code]
|
||
rpm: 40
|
||
c-medium-code:
|
||
novita: novita/qwen/qwen3-coder-30b-a3b-instruct
|
||
fallbacks: [b-medium-code, c-medium-ops]
|
||
rpm: 30
|
||
|
||
a-complex:
|
||
novita: novita/deepseek/deepseek-v3.2
|
||
fallbacks: [b-complex, a-reasoning]
|
||
rpm: 30
|
||
b-complex:
|
||
novita: novita/deepseek/deepseek-r1-0528
|
||
fallbacks: [a-complex, c-complex]
|
||
rpm: 20
|
||
c-complex:
|
||
novita: novita/deepseek/deepseek-r1-turbo
|
||
fallbacks: [b-complex]
|
||
rpm: 15
|
||
|
||
a-reasoning:
|
||
novita: novita/deepseek/deepseek-r1-0528-qwen3-8b
|
||
fallbacks: [b-reasoning, gemini-flash]
|
||
rpm: 30
|
||
b-reasoning:
|
||
novita: novita/deepseek/deepseek-r1-0528
|
||
fallbacks: [a-reasoning, c-reasoning]
|
||
rpm: 20
|
||
c-reasoning:
|
||
novita: novita/deepseek/deepseek-r1-turbo
|
||
fallbacks: [b-reasoning, gemini-flash]
|
||
rpm: 15
|
||
|
||
a-vision-ocr:
|
||
novita: novita/paddlepaddle/paddleocr-vl
|
||
fallbacks: [a-vision]
|
||
rpm: 30
|
||
no_escalation: true
|
||
a-vision:
|
||
novita: novita/qwen/qwen3-vl-30b-a3b-instruct
|
||
fallbacks: [a-vision-ocr]
|
||
rpm: 20
|
||
b-vision:
|
||
novita: novita/qwen/qwen2.5-vl-72b-instruct
|
||
fallbacks: [a-vision, c-vision]
|
||
rpm: 15
|
||
c-vision:
|
||
novita: novita/qwen/qwen3-vl-235b-a22b-instruct
|
||
fallbacks: [b-vision]
|
||
rpm: 10
|
||
|
||
optional_providers:
|
||
groq-llama-8b:
|
||
model: groq/llama-3.1-8b-instant
|
||
api_key: os.environ/GROQ_API_KEY
|
||
groq-qwen-coder:
|
||
model: groq/qwen-qwen-2.5-coder-32b
|
||
api_key: os.environ/GROQ_API_KEY
|
||
gemini-flash:
|
||
model: gemini/gemini-2.0-flash
|
||
api_key: os.environ/GEMINI_API_KEY
|
||
|
||
audit:
|
||
price_drift_threshold_pct: 10
|
||
cheaper_alternative_pct: 15
|