Transparent pricing for ongoing model usage

Starter and Pro both include strongest model access for coding workflows. The main difference is monthly request volume. When you exceed included requests, usage continues with pay-as-you-go.

Starter

$14.99 / month

Affordable access to top-tier coding AI for solo developers, debugging, and everyday development workflows.

1,200 requests / 30-day period
Up to 1M input tokens / request
Up to 100K output tokens / request
Strong model access included
Overage continues with pay-as-you-go

Best for solo developers. Start with Starter.

Pro

$37.99 / month

Built for daily usage, larger codebases, and teams who rely on AI-assisted coding throughout the week.

3,000 requests / 30-day period
Up to 1M input tokens / request
Up to 100K output tokens / request
Strong model access included
Overage continues with pay-as-you-go

Best for frequent usage. Choose Pro.

Feature	Starter	Pro
Price	$14.99	$37.99
Requests / 30-day period	1,200	3,000
Max input per request	1M tokens	1M tokens
Max output per request	100K tokens	100K tokens
Strong model access	Yes	Yes
Overage billing	Pay-as-you-go	Pay-as-you-go
Best for	Solo developers	Power users

Important billing notes

Request limits reset every 30 days from plan activation.
Overage usage is billed separately at standard usage rates.
Input and output token usage varies by workflow complexity and model choice.
Wallet top-ups remain available for pay-as-you-go usage.

Frequently asked questions

What counts as one request?
One API call to the chat completions endpoint.
What happens when I exceed my included requests?
Your service continues, and extra usage is billed via pay-as-you-go.
Do both plans include strongest model access?
Yes. Plan differentiation is about volume, not a weaker model tier.
Can I send large context windows?
Yes. Both plans support up to 1M input tokens per request.

Need the exact public model catalog first?

Browse current public model IDs, pricing, and limits before choosing a plan.

View Docs