Tools
what with, at what priceSheets for the tools that matter, use-case comparisons and step-by-step how-tos. Every price carries the date we checked it: an undated figure doesn’t get in here.
tool sheet
Claude Code: the coding agent in your terminal (and not just for programmers)
Anthropic's agent that reads, writes and executes in your environment: what it actually does, what it costs on the Pro and Max plans, and why it matters even if you don't develop.
Codex: the coding agent included in your ChatGPT subscription
OpenAI's agent lives inside the ChatGPT plan you may already have: open source CLI, web, editor and iPhone. What each plan includes and when it makes sense to choose it.
Cursor: the editor with the agent inside
For people who live in the editor rather than the terminal: Cursor puts the agent inside the development environment. Plans from zero to $200 a month, and a pricing model to understand before signing.
Local models: Ollama and LM Studio, when it actually makes sense
Running a model on your own computer is possible, for free: Ollama for the terminal, LM Studio for those who want an interface. What hardware it takes and when it pays off, no romanticism.
OpenCode: the open source coding agent where you pick the model
The terminal agent without lock-in: open source, connects to 75+ providers (OpenRouter included) and you decide the model, even a free or local one.
OpenRouter: every model with a single key
The one-stop shop for AI models: one account, one key, 400+ models from different labs. How billing works, what it really costs and where the limits are.
comparison
The gateways for trying models: OpenRouter, Together, Groq, Fireworks
OpenRouter is not the only counter: some host the open models, some run them on their own hardware, some bet everything on production. The map for choosing yours.
ChatGPT, Claude or Gemini: which subscription, read from the price lists
The most frequent question of all, answered with this site's method: the real tiers of the three price lists, what each includes, and the criterion for knowing when free is enough.
how-to
Reading benchmarks without getting played
SWE-bench, Terminal-Bench, LMArena, Artificial Analysis: what each one actually measures, how to read it in thirty seconds, and the three traps inflating every announcement.
OpenCode from zero to the first useful task
Install the open source agent, hook it to a model via OpenRouter and have it complete a real task in a fenced-off folder. Proof that a coding agent isn't just for developers.
OpenRouter in 15 minutes: from first sign-up to three models side by side
The step-by-step guide to opening the account, setting the spending cap before the money, and comparing three models on a case of yours. No coding required.