Coding Plan

A model subscription for your coding tool

Coding Plan includes Kimi K3, GLM-5.3, and DeepSeek V4.1 Flash. Switch models to suit each task, and choose a plan by usage allowance and peak-time priority.

Start coding Coding Plan pricing

Fix the rounding bug in invoice.ts

Review complete···

Round once, after adding the items.

Keep the calculation precise, then round the final total to two decimal places.

⌘ invoice.tsSuggested change

12 const total = items.reduce(13   (sum, item) => sum + item.price, 0);14 − return total;14 + return Math.round(total * 100) / 100;

✓ Patch ready for your review

Suggested regression checks0.1 + 0.2 → 0.30Empty invoice → 0.00Whole amount → unchanged

Want me to add these cases to invoice.test.ts?

＋Ask a follow-up…K3

Three models, in the coding tool you already use.

Every Coding Plan includes Kimi K3, GLM-5.3, and DeepSeek V4.1 Flash. Work with them in your terminal or in an app, and switch to suit each task.

Kimi K3

Take the hardest problems here: large refactors, unfamiliar code, and long debugging sessions.

GLM-5.3

Run most of the day on it: features, fixes, tests, and reviews.

DeepSeek V4.1 Flash

Hand it the quick, simple jobs at the lowest cost: small edits, renames, and boilerplate.

In the terminal

Claude Code and Codex CLI run all three on your plan. Each task can use a different model.

Claude Code

Codex CLI

~/app/invoiceKimi K3

❯ Fix the rounding bug in invoice.ts

Complete

● Read invoice.ts

● Edit invoice.ts

− return total;+ return Math.round(total * 100) / 100;

● Bash npm test

✓ 12 tests passed

✓ Done 1 file changed · Kimi K3

In an app

OpenCode runs the same three models today. Standard Code is coming soon.

OpenCode

Standard Code · Coming soon

Sessions

Invoice rounding

Checkout retries

Tax rules

Files

invoice.ts

invoice.test.ts

checkout.ts

Why is the invoice total off by a cent?

Review complete···

Floating-point sums drift.

Prices are added as floats, so tiny errors accumulate. Round once, at the end.

⌘ invoice.tsSuggested change

+ return Math.round(total * 100) / 100;

Suggested check: Decimal total → 0.30

Ready for the next change.

＋Ask a follow-up…Kimi K3

Choose your allowance and peak-time priority.

Every plan includes all three models. During busy periods, the $200 plan has priority over $100, followed by $50.

Compare plan details

$50 per developer, per month

5-hour + weekly limits
Smaller usage allowance, with both 5-hour and weekly limits.
Peak-time restrictions apply. Lowest priority.

Get $50 plan

$100 per developer, per month

Weekly limit only
Larger usage allowance, with a weekly limit and no 5-hour limit.
Peak-time restrictions apply. Priority above $50, below $200.

Get $100 plan

$200 per developer, per month

Highest priority

No usage cap
No 5-hour or weekly limits, and no total usage cap.
Peak-time restrictions still apply. Highest priority.

Get $200 plan

Peak-time restrictions apply to every plan: requests may slow, queue, or time out. Priority is $200 → $100 → $50.

Check two sets of data rules.

Your coding tool controls project access and local history. Standard Thinking’s data terms cover the inference requests sent to us.

Read the data processing policy

Project context

Check which files, instructions, and conversation context the tool can use.

Stored content

Check what persists between tasks and the controls for removing stored context.

Model training

Inputs and outputs are not used to train public or shared models without separate, explicit opt-in.

Choose the right product for the work.

Coding Plan covers a developer’s own work. AI features delivered to your users use Standard API or Product Plan.

Building a product for customers?

Use Standard API for token-billed requests or Product Plan for a monthly plan for your product.

How do the allowances work?

The $50 plan has a smaller allowance with both 5-hour and weekly limits. The $100 plan has a larger allowance with only a weekly limit. The $200 plan has no 5-hour, weekly, or total usage cap. All plans remain subject to peak-time restrictions, with priority in the order $200 → $100 → $50. How coding plans count usage compares the units and reset windows other plans publish.

Which tools are supported?

Claude Code, Codex CLI, and OpenCode are supported, and Standard Code is coming soon. Ask about your workflow for setup instructions. Which coding tools connect to an OpenAI-compatible endpoint lists what each tool’s maker documents.