Rate limits per plan
| Plan | Requests / min | Input tokens / min | Output tokens / min | Max concurrent |
|---|---|---|---|---|
| Basic | 600 | 2,000,000 | 500,000 | 50 |
| Pro | 2,000 | 5,000,000 | 1,500,000 | 200 |
| Enterprise | Custom rate limits, sized per organization to your workload. | |||
How the limits work
Four dimensions, checked on every request:- Requests / min: how many new requests your organization can start each minute.
- Input tokens / min: prompt tokens the models may process per minute.
- Output tokens / min: tokens the models may generate per minute, limited separately from input because generation, not reading, is the scarce direction.
- Max concurrent: how many requests may be in flight at the same moment.
429: back off briefly and retry, see error handling.
Requesting Pro or Enterprise
Plan changes are handled by our team, not self-serve. From the dashboard:1
Open the plans dialog
Sign in and click Upgrade Plan in the sidebar (it reads Your Plan on organizations already on Pro or Enterprise).
2
Request a plan upgrade
Pick the plan you are asking for and click GET A QUOTE on its card: Pro for higher fixed limits, or Enterprise for custom rate limits sized to your workload. The quote form is the same either way, so describe what you need: volume, the requests, tokens, and concurrency your traffic requires, regions, support. There is no unlimited plan to switch on, so for Enterprise state the limits explicitly and we configure them for your organization. Our team reaches out, usually within one business day. Enterprise also unlocks data residency, monthly invoicing, and dedicated compute. The dashboard’s Support tab reaches the same team.