110 free AI models, tested


110 free AI models, tested
16 providers, what's actually free, and the catches each one hides. Plus 3 more reads.  ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌
WotAI

110 free AI models, tested

Hey Reader,

Four reads this week. The first two go together: where the free AI models actually are, and how to put Claude Code in charge of them.

110 free AI models, and what each one actually costs you

The best free LLM APIs in 2026 – a live-probed directory of free models across 16 providers

Sixteen providers hand out real API access right now. Not trials. Free tiers, running today.

The catch is that "free" is doing different work at each one. Somewhere it means twenty requests a minute and then you're throttled. Somewhere else it means your prompts are training data. And some models are just gone one morning with no notice.

Which is why the list is probed live instead of copied off sixteen marketing pages. ~110 free models, ranked by what's genuinely free, and the specific catch each provider buries.

See the list →

Put Claude Code in charge of the free pool

Claude Code orchestrating a pool of free LLM APIs, delegating grunt work and spending budget only on hard tasks

A pile of free models isn't worth much on its own. Something has to decide what goes where.

Make that something Claude Code. It reads the task, drops the grunt work down to the free pool, and spends real budget only where judgment is involved. Sixteen free tiers stacked behind one endpoint, with the expensive model deciding what's beneath it.

Claude Code stays the brain. It stops being the typist.

Read the setup →

Give Claude Code a full product team

WoterClip routing GitHub issues to a 13-role AI product team inside Claude Code

Different problem this time.

If your work moves through GitHub issues, the code is rarely what slows you down. It's the scaffolding around it. Writing the PRD. Splitting it into stories. Sizing the sprint. Arguing with yourself about what ships first. Remembering to check the QA.

WoterClip gives each issue to a persona agent that owns that role. This one walks importing a 13-role product team – PRD writer, story writer, sprint manager, prioritization, QA, risk, roadmap, OKR, release – and getting your first heartbeat running in about five minutes.

Meet the team →

WoterClip v0.2.0: GitHub Issues replaces Linear

WoterClip v0.2.0 swapping its tracker backend from Linear to GitHub Issues via the gh CLI

And the change that made the above possible. v0.2.0 drops Linear for GitHub Issues. No MCP, no external tracker, just the gh CLI already sitting on your machine.

One warning if you ran v1: a few concept mappings fail silently when you migrate. Silently is the worst way for anything to fail, so they're all written out in the post with the config changes next to them.

See what changed →


Reply and tell me which one was the read for you. I read every reply.

– Alex


Alex Kim builds with Claude Code every day. He wrote WoterClip, the open-source plugin that hands your GitHub issues to AI agents, and built Flow and Echo.

P.S. – The conversations behind reads like these happen in the WotAI Skool community. 760+ builders, three live calls a week, free to jump in.

Come build with us

Follow WotAI: LinkedIn  ·  YouTube  ·  TikTok

WotAI · AI Automation that Actually Ships

wotai.co

WotAI · 440 N. Barranca Ave., Unit 3777, Covina, CA 91723

WotAI

If you're building with Claude Code, n8n, or AI agents in production, this is the email I'd want. Weekly recap of what shipped, what broke, and how I'm running it. Specific over vague. Replies welcome.

Read more from WotAI
The most powerful AI model lasted three days

The most powerful AI model lasted three days What it means for your business – and the one move that kept some teams calm. Plus 2 more reads. The most powerful AI model lasted three days Hey Reader, Anthropic shipped its most powerful model in years on June 9. Three days later, the US government pulled it offline – for everyone. If you run a business on AI, the story to take away isn't the politics. It's the quiet lesson it handed every operator about how to set up your stack. Anthropic's...

Open Design, running in 10 minutes The full setup on Claude Code, plus the #1 install gotcha. And 2 more reads. Open Design, running in 10 minutes Hey Reader, Open Design auto-detects 16 coding-agent CLIs and lets you swap engines with one click. The hard part is getting it running the first time. This week opens with the 10-minute setup on Claude Code, plus two more reads behind it. Open Design, running on your machine in 10 minutes Open Design runs locally with Claude Code as the engine:...

The Opus 4.8 number nobody's posting

The Opus 4.8 number nobody's posting Not the coding score. Plus Open Design at 4 weeks, and 2 more reads. The Opus 4.8 number nobody's posting Hey Reader, Anthropic shipped Claude Opus 4.8 this week, and the whole feed posted the same screenshot – the coding score. That's the least interesting part. The number that actually changes how you work is below, plus three more reads stacked behind it. Claude Opus 4.8 – the number nobody's posting Everyone screenshotted the coding score (64.3% to...