Question 1

Does Pier run locally?

Accepted Answer

Yes. The CLI runs as a single binary on your machine. In local-only mode your code never leaves your environment; cloud model calls are opt-in and clearly indicated.

Question 2

Which languages and frameworks are supported?

Accepted Answer

Any text-based codebase: TypeScript, Python, Go, Rust, Java, and more. It learns your project's conventions rather than assuming a stack.

Question 3

Can I prompt in Indian languages?

Accepted Answer

Yes. You can describe tasks in English, Hindi, Tamil, Kannada, Telugu and others. It reasons over your intent regardless of the language you type in.

Question 4

What's included in the $5 Pro plan?

Accepted Answer

Pro is $5 a month and gives you the full Pier agent: multi-repo context, Indian-language prompting, and the option to plug in DeepSeek or Claude for hard tasks. It comes with a monthly pool of usage credits that covers typical day-to-day coding.

Question 5

What happens if I run out of credits?

Accepted Answer

Buy a $5 usage pack any time, even mid-session. Packs stack, charge the same per-token rates as Pro, and the credits don't expire, so you only pay for what you actually use beyond the monthly pool.

Question 6

How can Pier be this much cheaper?

Accepted Answer

Sovereign Indian models are trained and hosted in Bharat and priced far below frontier US models: a fraction of a cent per million input tokens versus dollars elsewhere. A coding agent reads far more than it writes, so those input savings compound across every repo read, diff, and tool result.

Question 7

Is a cheaper model good enough for real coding?

Accepted Answer

For everyday work (planning, codebase Q&A, refactors, test fixing), our sovereign Indian models hold their own and are competitive on standalone coding benchmarks like LiveCodeBench. For the hardest long-horizon repo tasks you can plug in DeepSeek-V4 or Claude per run, so you only pay frontier prices when you actually need frontier quality.

Question 8

What does Pier send off my machine?

Accepted Answer

Only the model prompt for the calls a task actually needs: the slices of code, diffs, and tool output the agent reads to reason about your task, sent to the model provider over TLS. In local-only mode nothing leaves your machine. Cloud calls are opt-in and clearly indicated before they run.

Question 9

Is my code stored on your servers?

Accepted Answer

No. Pier does not retain your source code on our servers. Prompts are processed to generate a response and are not used to train models. Account and billing data is the only thing we keep, and you can request its deletion at any time.

Model	Input	Output	Blended80/20
Pier 105BPier	$0.04	$0.17	$0.07
DeepSeek-V4 FlashCheap & fast	$0.14	$0.28	$0.17
DeepSeek-V4 ProCost / performance	$0.44	$0.87	$0.52
Claude Opus 4.8Quality ceiling	$5.00	$25.00	$9.00

Simple, honest pricing.

Pro

Max

Usage pack

What a million tokens costs

Questions, answered

Keep exploring

Cost per task

Use cases

Security

Begin here