Pricing
Plans
| Plan | Monthly | Key surface | Seat model | Checkout |
|---|---|---|---|---|
| Starter | $10 | On-ramp tier for evaluation -- cache-friendly daily usage, monthly billing | Solo | Subscribe |
| Pro | $20 | Pro coding -- the default for most coding work | Solo | Subscribe |
| Max | $100 | Heavy daily sessions -- highest solo quota envelope | Solo | Subscribe |
| Team | $25 / seat | Pro-equivalent per seat plus hosted codebase indexing for the org (monthly only) | Per-seat | Subscribe |
| Team Max | $100 / seat | Max-equivalent per seat plus hosted codebase indexing for the org (monthly only) | Per-seat | Subscribe |
Solo plans also offer an annual option (Starter $100, Pro $200, Max $1,000) -- a two-month discount on the monthly rate. Team and Team Max ship monthly only for V1; annual per-seat is deliberately deferred (see the pricing details page).
Local context works everywhere -- the typed CLI, Cursor, Continue, Claude Code, and any Anthropic-API-compatible client reads files on your machine. Hosted codebase indexing is an additional surface for Team and Team Max orgs that want a shared, server-side index across seats; it is not a missing feature on solo tiers.
Cancellation takes effect at the next renewal; the remainder of your paid period is served normally. Team / Team Max codebases retain a 30-day grace post-cancellation, then hard-delete within 14 days.
Compared to subscription AI CLIs
| Reference Pro plan | typed Pro | Reference Max plan | typed Max | |
|---|---|---|---|---|
| Monthly | $20 | $20 (same) | $100 | $100 (same) |
| Annual | $200 | $200 (same) | not offered | $1,000 (the reference Max plan offers no annual) |
| Monthly usage | Pro plan standard tier | More tokens than a typical Pro plan at the same monthly price | Max plan standard tier | More tokens than a typical Max plan at the same monthly price |
| Image input | yes | yes | yes | yes |
| Context window | 200K-1M depending on tier | ~500K every text tier, auto-upgrades to ~950K for long-context; ~500K multimodal | 200K-1M depending on tier | ~500K every text tier, auto-upgrades to ~950K for long-context; ~500K multimodal |
| Prompt caching | yes | yes (best on typed-xhigh tier) |
yes | yes (best on typed-xhigh tier) |
| Overage available | yes (Extra Usage) | yes (top-ups) | yes (Extra Usage) | yes (top-ups) |
| Overage rate (input) | $1-5 / M tokens (current gen) | $1.67 / M (~44-67% cheaper vs mid/top-tier rates) | $1-5 / M tokens (current gen) | $1.67 / M (~44-67% cheaper vs mid/top-tier rates) |
| Overage rate (output) | $5-25 / M tokens (current gen) | $8.33 / M (~44-67% cheaper vs mid/top-tier rates) | $5-25 / M tokens (current gen) | $8.33 / M (~44-67% cheaper vs mid/top-tier rates) |
| Billing structure | 5-hour windows + weekly | Monthly with auto-top-up at quota | 5-hour windows + weekly | Monthly with auto-top-up at quota |
Same monthly price. Matched monthly usage. Overage rates roughly half. Annual Max plan the reference CLIs do not offer. Monthly billing instead of rolling 5-hour windows.
Cheaper per token means more tokens per dollar. Every overage dollar at typed buys ~1.8x more tokens than typical Extra Usage at mid-tier rates, and ~3x more at top-tier rates. Combined with the matched monthly subscription, your total monthly spend goes further at typed.
A note on the model
typed runs its own inference tier set under the hood. Read the full honest comparison →
Top-ups
Customers on any paid tier can buy additional usage in fixed denominations: $5, $10, $20, or $50. Each top-up adds both input and output tokens to your remaining balance -- roughly half the going overage rate elsewhere.
| Top-up | Input tokens added | Output tokens added |
|---|---|---|
| $5 | 1.5M | 300K |
| $10 | 3M | 600K |
| $20 | 6M | 1.2M |
| $50 | 15M | 3M |
- Effective rate: $1.67 / M input, $8.33 / M output.
- Top-ups expire 90 days from purchase.
- Consumed before the next month's quota refills (use-it-or-lose-it).
- One-click purchase from the dashboard or in response to an API quota-exceeded error.
Auto-top-up at quota: optional, opt-in
By default, requests past your monthly quota return HTTP 429 with a one-click top-up prompt -- pick a $5/$10/$20/$50 denomination and continue. If you'd rather skip the interruption, enable auto-top-up in your dashboard and the next request past quota auto-charges your chosen denomination, sends a receipt by email, and your session continues without prompting.
| Usage | Behavior |
|---|---|
| 0% - 80% | Normal. No banner, no friction. |
| 80% - 100% | In-app banner; email warning showing how many tokens remain. |
| 100% and beyond, auto-top-up off (default) | HTTP 429 with a one-click top-up prompt -- pick a denomination and continue. |
| 100% and beyond, auto-top-up on | Next request auto-charges your configured denomination; session continues without interruption; receipt emailed. |
Settings live in your dashboard: toggle on/off, denomination ($5/$10/$20/$50), and an optional monthly ceiling that limits how much auto-top-up can charge in a calendar month.
Sales-final policy
All sales final. Cancellations take effect at the next renewal -- the remainder of your paid period is served normally. We process discretionary refunds on a case-by-case basis for billing errors or extended service outages on our side -- email support@typed.cloud. We do not promise an automatic refund window because cost-of-goods scales with usage, and we would rather be honest about the economics than build the refund into the price.
If you are not sure typed will work for your workflow, the right thing to do is pay for one month, try it for a week, and cancel before renewal if it does not suit you. The remaining three weeks still serve normally. That is the trial.
For the token-level methodology behind these numbers, see pricing details. For a full side-by-side including model differences, see the honest comparison and migration guide.