Skip to content
All tags

#cost-control

2 posts
tech deep-dive

Building a Taiwan Stock Research Agent (Part 3): Tiered LLMs and a Degradation Chain—API, Local CLI, and Dictionary Fallbacks

Only two roles call an LLM; every other analyst remains fully programmatic. Each call follows an Anthropic API → local Claude CLI → rules-based degradation chain, and cost accounting trusts only provider-reported values—unknown cost is never treated as $0.

#stock-research-agent#langgraph#ai-agent#llm-ops#cost-control#observability
ai guide The RAG Techniques Compendium

RAG Quota System: Controlling LLM Costs with Dual Limits

Limiting request count alone is not enough — a single long query can consume ten times the tokens of a normal one. Dual quotas (request count + token count) are what truly control costs.

#rag#quota#rate-limiting#token-budget#cost-control#cloudflare-workers