VPS with GPU: when you actually need one
A GPU on a VPS buys batch throughput and room for large models. Quantized chat models, embeddings and Whisper small run fine on CPU. Start there, measure.
#ai
Filtering by topic #ai · clear
AI agent cost control on an always-on VPS
An unattended agent bills every loop with nobody watching. Hard caps, task budgets, prompt caching, batching, and the usage fields that show the spend.
Host Ollama on a VPS: self-host an LLM safely
A 7B model wants 8 GB of RAM and gives 4 to 10 tokens per second on CPU. Host one on a VPS and call it at 127.0.0.1:11434/v1, with port 11434 kept closed.
Claude + n8n: build AI workflows on a VPS
Connect Claude to n8n on your own VPS: an integration guide with credentials, model choice per node, three worked AI workflows, cost math, and common errors.
Claude API tutorial: your first app on a VPS
Get a Claude API key, secure it on Ubuntu 24.04, ship a Python log-explainer with streaming, typed error handling, and real cost control.
Anthropic Claude API: no free tier, but a credit
The Claude API has no free tier. New accounts get a small signup credit, and several parts cost nothing. October 2026 rates plus a worked cost for a first app.
Claude usage limits: what to do when you hit one
Switching models only fixes a model family limit. How Claude subscription session and weekly limits differ from API 429 rate limits, and what to do next.
Self-hosted AI image generator: real specs
The honest hardware ladder for running Stable Diffusion yourself: what a CPU VPS can do, what SDXL needs, ComfyUI install commands, and disk you should budget.
Which Claude model should I use? Cost guide
Opus 5.5, Sonnet 5.5 or Haiku 5.5? The October 2026 rates per model, a worked cost comparison on 100,000 jobs, and the settings that move a bill most.
Is the Claude API cheaper than a subscription?
Metered API billing or a flat plan? Here is the break-even arithmetic on current per-token rates, and what moves it further than the plan fee does.
What are Claude tokens? Claude Code's token math
A Claude token is a few characters. See why a Claude Code turn can bill 80,000 tokens and why five idle minutes on an API key can make the next turn cost 5x.
Which Claude plan do you need in 2026?
Free, Pro, Max, Team or Enterprise? Match the 2026 tiers to the way you work: which plans include Claude Code, and when Team beats five Pro accounts.
Claude for students: what it costs in 2026
There is no individual student discount on Claude as of October 2026. Here is the free tier, the university route, and a coursework month costed on the API.
Claude free tier: what the limits actually are
What the Claude free plan includes, how its usage limits are counted and reset, why the API has no free tier, and when paying starts to pay off.
Run Gemini CLI on a headless VPS
Run Google's Gemini CLI on a headless VPS: a current Node, a no-sudo global install, browserless API-key auth, and tmux so long tasks survive SSH drops.
Claude Code context: stop slow, costly sessions
Every turn re-sends your whole context, so a long session slows down and costs more. Read /context, cut the fixed tax, then clear and compact with intent.