Use the right AI model and tool for each job, this month.
For coding, research, content, outreach, data, operations, browsing and voice: the current best pick, the runner-up, what it costs and what to avoid. Rewritten weekly from release notes, benchmarks, pricing and hands-on findings.
Free on Explorer. No card.
From this week's guide
Real output from Spezia, read from the same data the tool uses. Every line links to its source.
Claude Opus 5.5 is now the first genuinely publishable AI writer and the strongest software model, while OpenAI's cheaper small models (GPT-6.1 Terra) take over browser automation and high-volume agent work.
- Software engineering and coding agents
Claude Opus 5.5 in Claude Code
Expert hands-on finding that Claude is much better than alternatives for software engineering, and Claude Code's release notes show active investment in agent task management, spend tracking and latency tuning.
Cost: $4/$20 per 1M input/output tokens
- Browser use and web automation
GPT-6.1 Terra in ChatGPT Work / Codex
Expert finding that OpenAI models are more token-efficient than Claude for browser use, and Terra is explicitly designed for fast, efficient computer use at scale with a 75% cost cut versus Haiku 4.5.
Cost: 75% less than Haiku 4.5
- Content and media: writing, design, video
Claude Opus 5.5 in Claude apps (Pro/Max/Team)
Expert finding that Opus 5.5 is the first model where AI-produced content is genuinely publishable; Max and Team plans now include monthly API credits for running content agents.
Cost: $4/$20 per 1M input/output tokens
- Outreach and sales: email, LinkedIn, CRM
GPT-6.1 Terra in ChatGPT Work / Codex
Expert note directs browser-run outreach to OpenAI for token efficiency, and Terra is the cheap high-volume computer-use model.
Cost: 75% less than Haiku 4.5
Nobody pays to be listed. Picks come from release notes, published results, pricing and hands-on use.
What you get
A pick for each job
Eight kinds of work, each with a ranked short list and one sentence on why.
What to avoid
The setups that waste money or time right now are named as plainly as the ones that work.
Current, not last quarter
Tools change monthly. The guide is rewritten every week and each pick cites where it came from.
How it works
- 1Open Tooling and find the kind of work you do.
- 2Read the top pick, its cost and its sources.
- 3Ask Spezia for exact setup steps and a prompt to paste.
Who uses it
Questions about Tooling guide
Is Spezia paid by any vendor?
No. Picks come from release notes, published results, pricing and hands-on use. Nobody pays to be listed.
Is it free?
Yes. The tooling guide is part of Explorer.
Research from this data
Analysis written from what Tooling guide tracks, with the sources and the day each figure was read.
- AI tools and modelsLiveWeeklypicks for each job, rewritten from release notes and results
The best AI model and tool for each job, updated every week
The best AI model and tool for coding, research, content and more, with the reason, the cost and what to avoid. Read live from Spezia's weekly guide.
- AI research and securityAnalysis89%Chinese share of open-source model spend, in Menlo's estimate
Open-source AI models in 2026: who leads, and what the 89% Chinese share means
Which open-weight AI models lead in November 2026, what Menlo's 89% Chinese share of open-source spend measures, and which releases are shipped or pending.
Often used with
Software watch
NewFreeNew models, features, prices and limits, the day they ship.
See it liveSpezia for your AI agent
NewFreeConnect Spezia to Claude Code, Codex, Cursor and other agents in one step.
See it liveAsk Spezia
Start hereFreeAn analyst that answers from verified data, with a source on every figure.
See it live
Use the right AI model and tool for each job, this month.
Free on Explorer, with 5 questions a month to Ask Spezia. No card.