Docs · Plans

Free plan

Two fast models, no card.

Price

$0 / month

Credits

$10 / month

Requests

~11.5K

Models

2

Getting the plan#

Connect GitHub to access the Free plan. Sign up with GitHub, or sign up with email and connect GitHub from your account. The plan starts the moment GitHub is connected.

Each GitHub account unlocks the Free plan for one CCode account, and stays tied to that account.

Requests included#

The Free plan includes $10 of credits a month, spent at each model maker's official API price. On DeepSeek V4.1 Flash, that is about 11,574 requests.

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 DeepSeek V4.1 Flash that step costs $0.0009, so $10 ÷ $0.0009 ≈ 11,574. Both included models are cheap per step, so the credits go a long way:

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#

The Free plan runs on the 2 models below. You can spend the whole $10 on one of them or mix them. Want Claude Opus 5.5 or GPT-6.1 Sol? They come with Starter and Pro.

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 $10 across the whole month, so a long session today still leaves plenty for tomorrow.

Up to 4 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#

No card needed, and your credits refresh every month. Need more? Starter gives you $5 of credits for $1 a month.