On this page⌄

Docs · Plans

Pro plan

Seven times the usage. For coding every day.

Price
$10 / month
Credits
$70 / month
Requests
~2.3K
Models
All 21

Requests included#

The Pro plan includes $70 of credits a month, spent at each model maker's official API price. On Claude Sonnet 5.5, that is about 2,380 requests, from the $35 that can go to Claude models each month.

A request is one agent step: the conversation so far (about 50K tokens, read from the prompt cache), about 1K new tokens and a 220-token answer. On Claude Sonnet 5.5 that step costs $0.0147, so $35 ÷ $0.0147 ≈ 2,380. Cheaper models stretch the same credits further:

DeepSeek V4.1 Flash
81K
GLM 5.3 Flash
39.7K
DeepSeek V4 Pro
15.9K
GPT-6.1 Sol
7.6K
Claude Haiku 4.5
4.7K
GLM 5.2
4.5K
GPT-5.6 Sol
2.4K
Claude Sonnet 5.5
2.3K
Claude Opus 5.5
1.8K
Requests per month on the Pro plan, by model

Short questions use fewer credits; big files and long reasoning use more. The CCode sidebar shows what each session has spent as you go.

Models#

Credits work on all 21 models from Anthropic, OpenAI, DeepSeek and Z.ai. Mix them however you like: up to $35 a month can go to Claude models, and the full $70 to any other model. The four below are the ones most people start with; the full price table lists the rest.

Claude Opus 5.5

Anthropic

Hard problems: large refactors, subtle bugs, architecture.

Input
$4
Cached
$0.20
Output
$20

$35 covers ~1.8K requests

GPT-6.1 Sol

OpenAI

Everyday coding, reviews and tests, at about half Opus's cost per step.

Input
$2
Cached
$0.10
Output
$10

$70 covers ~7.6K requests

DeepSeek V4.1 Flash

DeepSeek

Fast, cheap iterations and long agent loops.

Input
$0.30
Cached
$0.006
Output
$1.20

$70 covers ~81K requests

GLM 5.2

Z.ai

A strong open model for routine work at a low price.

Input
$1.40
Cached
$0.26
Output
$4.40

$70 covers ~4.5K requests

Prices in USD per 1M tokens.

How usage refreshes#

Your usage refills on three schedules: every 5 hours, every week and every month. That spreads your $70 across the whole month, so a long session today still leaves plenty for tomorrow.

Every 5 hours
$14
Every week
$35
Every month
$70
Usage available in each window

Up to 8 requests can run at once, so helpers can work in parallel.

Prompt caching#

Long sessions stay affordable: whatever the model has already seen in your conversation is billed at its cached rate, up to 95% below the input price, so even deep into a task each step costs just cents.

Billing#

Your plan renews every month and your credits refresh with it.

Pro · $10/month for $70 of credits

Get Pro