Why Twin

Delegate real work on the web — and stay in control

Hand your agent the whole web: it reaches any site, pulls any data, and signs into the accounts you connect, while you set the guardrails and approve what matters. And because repeated workflows replay from cache, your cost per run falls as you scale — instead of climbing with every run.

The problem

Browser infra for agents bills you to think twice

The unit changes — browser-hours, steps, gigabytes — but the economics rhyme: the LLM drives the page on every execution, so cost scales linearly with usage.

Run a 50-step authenticated workflow a thousand times and you’ve paid the model to re-read the same DOM and re-decide the same clicks a thousand times. Whether the bill says browser-hours (Browserbase, Steel), steps and tokens (Browser Use), or gigabytes (Bright Data), the curve points the same way: up and to the right, in lockstep with how much your agents actually work.

That’s backwards. The most valuable workflows are the repetitive, authenticated ones you run at volume — exactly the ones a per-run LLM bill punishes hardest. See the full breakdown on the comparison pages and the alternatives index.

The curve

Two cost curves, one decision

Illustrative shape, not a quote — the point is the direction. As the same workflow runs more often, a re-run-the-LLM model holds flat (or rises); Twin falls toward the replay floor.

Re-run the LLM every time

Cost per run is roughly constant — the model reads the page and decides the clicks again on every execution. 1,000 runs cost ~1,000× a single run. Volume is a liability.

run #1~$0.06
run #100~$0.06
run #1,000~$0.06

Twin: compile once, then replay

Run #1 pays the cold compile. After that, semantic cache hits replay deterministically at ~$0 LLM, so the blended cost per run falls as usage grows — a cache hit is ~5× cheaper, and the marginal cost per run trends toward zero.

run #1 (cold compile)~$0.06
run #100 (cache hit)~$0.012
run #1,000 (replay)→ ~$0

Numbers are illustrative to show the shape of the curve, not a benchmark or a guarantee. LLM cost is metered and passed through at 1× — see the live rate card at pricing.

Who it’s for

Built for the teams that run the browser at volume

If you need an agent that does real web work you can hand off and still govern — accounts you authorize, steps you approve, a full audit trail — with a cost curve that falls as you scale, Twin is the layer.

  • Teams building AI agents that need a browser they can trust to repeat.
  • RPA-replacement products running authenticated, multi-step flows on a schedule.
  • Anyone whose per-run model bill has become the line item that scales with success.