Back to feed
Dev.to
Dev.to
6/11/2026
I built an AI chat over my CV on a zero-pound inference budget

I built an AI chat over my CV on a zero-pound inference budget

Short summary

Built ask.hiten.dev, a streaming CV chatbot with zero inference costs by chaining free-tier LLM providers (Groq → OpenRouter → NVIDIA → Cerebras) with automatic failover to survive rate limits. Uses stream normalization to fix model quirks, fact whitelisting to prevent hallucinations, and in-memory caching for fixed prompts. Deployed serverless on Oracle free-tier VM with Astro SSR.

  • •Built zero-cost CV chatbot by chaining 4 free LLM providers with automatic failover for reliability
  • •Normalizes model output in code (quotes, dashes), whitelists facts to prevent hallucinations
  • •Caches fixed prompts in-memory; validated with Playwright tests; deployed on free Oracle VM

Generated with AI, which can make mistakes.

#ai-tools#open-source
Read full article at Dev.to

Is this a good recommendation for you?

Explore more

How I Built a Suite of 8 AI Tools with $0/Month in API Costs Using NVIDIA NIM
Dev.to
Developer builds free voice AI
Dev.to
How I built a 3-provider LLM fallback system in production (and what actually broke)
Dev.to
How I Built a Free Python Practice Platform With Zero Server Costs Using Groq and Supabase
Dev.to