An AI coding service that speaks the Anthropic API. Three env vars to switch from Claude. Same monthly price, 44-67% cheaper overage on Sonnet/Opus, monthly billing instead of 5-hour reset windows.
Today we're launching typed - an AI coding service that speaks the Anthropic API. If you use Claude Code, Cursor, Cline, or any Anthropic-compatible client, you can switch to typed by setting three environment variables. Pricing matches Claude Pro and Claude Max 5x exactly. Overage costs 44-67% less than Claude's Extra Usage on Sonnet or Opus. Billing is monthly, with no 5-hour reset windows.
typed runs a different model than Claude under the hood. Most coding workflows feel identical; the migration page calls out where they don't.
export ANTHROPIC_BASE_URL=https://api.typed.cloud
export ANTHROPIC_API_KEY=<your typed key>
export ANTHROPIC_MODEL=typed-xhighRestart your client. That's it. The API is wire-compatible - we run our own day-to-day on Claude Code against typed, and other Anthropic-API-compatible clients (Cursor, Cline, Roo Code) should work the same way. Any tool that reads ANTHROPIC_API_KEY and accepts a base-URL + model override talks to typed exactly the way it talks to Claude.
The third line is required: typed uses its own model identifiers (typed-xhigh is the default; typed-max, typed-high, typed-medium, typed-low, and typed-minimal are also available). The full per-tier breakdown lives on the migration page.
You can flip back to Claude at any time by swapping the variables. typed and Claude can coexist on the same machine for the same client. There's no lock-in to worry about.
| Claude Pro | typed Pro | Claude Max 5x | typed Max | |
|---|---|---|---|---|
| Monthly | $20 | $20 | $100 | $100 |
| Annual | $200 | $200 | not offered | $1,000 |
| Monthly usage | Claude Pro standard | At least Claude Pro's capacity | Claude Max 5x standard | At least Claude Max 5x's capacity |
| Context window | 200K default (1M via beta header) | ~192K reasoning tiers; ~1M fast tiers; ~262K multimodal | 200K default (1M via beta header) | ~192K reasoning tiers; ~1M fast tiers; ~262K multimodal |
| Prompt caching | yes | yes | yes | yes |
| Image input | yes | yes | yes | yes |
| Overage (input) | $1-5 / M (Haiku to Opus) | $1.67 / M | $1-5 / M (Haiku to Opus) | $1.67 / M |
| Overage (output) | $5-25 / M (Haiku to Opus) | $8.33 / M | $5-25 / M (Haiku to Opus) | $8.33 / M |
| Billing reset | rolling 5h + weekly | monthly | rolling 5h + weekly | monthly |
We don't claim to be cheaper than Claude. The subscription price is the same. The things that are different:
A Starter tier exists at $10/month (roughly one-third of Claude Pro's monthly usage) for lighter workloads. Top-ups work on every paid tier.
CLAUDE.md) get cache discounts automatically - you don't opt in.The full honest comparison lives at typed.cloud/migrate. If you're evaluating, read it first.
Take a Claude Pro user on Sonnet (Claude's default coding tier) who consistently spends an extra $40/month on Extra Usage to finish the work the tier doesn't cover.
| Claude Pro + Extra Usage | typed Pro + top-ups | |
|---|---|---|
| Subscription | $20 | $20 |
| Overage spend | $40 (Sonnet rates: $3/M input, $15/M output) | ~$22 (at $1.67/M input, $8.33/M output) |
| Total | ~$60/mo | ~$42/mo |
| Reset window | 5h rolling + weekly | monthly |
The subscription doesn't move. The overage line item does. For a Max-tier user paying Opus rates on Extra Usage, the gap is much bigger -- typed top-ups stay flat at $1.67/M and $8.33/M regardless of which Claude model you'd otherwise be paying for.
We're not claiming this math is universal. If your monthly usage fits inside Claude Pro and you never hit overage, the two products cost the same and you should pick whichever you prefer.
If you're evaluating typed for a privacy-sensitive workload, read the privacy policy first. It's the disclosure surface.
ANTHROPIC_BASE_URL=https://api.typed.cloud, ANTHROPIC_API_KEY=<your typed key>, and ANTHROPIC_MODEL=typed-xhigh in your client.If you decide typed isn't for you, swap the variables back. You're never locked in.
Yaw Labs builds developer tools. We've been Claude Code users since launch. Two things consistently came up across our own usage and from customers on the Yaw Terminal community:
typed is what we wanted as Claude customers. We anchored pricing to Claude's because we think anchoring is honest, and we put the savings into the overage rate because that's where the real money goes for heavy users.
If you've felt either of those problems, give typed an afternoon. The switch costs you three env vars, and you can evaluate it on the Starter tier for $10 - less than half a Claude Pro subscription. Keep Claude as your primary; fall back to typed when the windows or overage bite.
Drop-in fallback for Claude Code, at the same monthly price.
Three env vars to switch. 44-67% cheaper overage on Sonnet/Opus. Monthly billing, no 5-hour windows. Magic-link signup, no lock-in.
Team and Team Max ship today for orgs that want shared billing and a hosted codebase index. Typed Team is $25/seat/month and carries the Pro-equivalent quota envelope per seat; Typed Team Max is $100/seat/month and carries the Max-equivalent quota envelope per seat. Both are monthly only for V1 - per-seat annual is deliberately deferred and we will revisit if customers ask. The whole subscription bills at per_seat_price * seat_count under our payment processor's volume pricing scheme.
The new surface Team and Team Max add is hosted codebase indexing. Local context works everywhere, on every tier and every Anthropic-API-compatible client; hosted indexing is the additional convenience for orgs that want a shared, server-side index across seats. It is not a missing feature on solo tiers. Storage and processing stay inside our us-west-2 AWS region, access is org-scoped, and codebases retain a 30-day grace post-cancellation before hard-delete.
Current pricing for all five tiers lives at typed.cloud/pricing.
Published by Yaw Labs.