Plans and quota
New dollar credits against the old session and weekly windows, and how to tell which plan you are on.
The new plans
Ollama Cloud now sells plans with usage credits. Usage is measured in tokens, at each model’s own rates for input, cached input and output.
| Plan | Price | Included credits a month | Concurrent requests |
|---|---|---|---|
| Free | Free | Starter credits, starter models only | 1 |
| Pro | $20 a month, or $200 a year ($16.67 a month billed annually) | $60 | 3 |
| Max | $100 a month | $300 | 10 |
| Team (early access) | $500 a month | $1,000, shared across users | 10 |
Enterprise is custom-priced, with model access controls and cost budgets per user and per API key.
How included credits work
- Included plan credits are used first. Purchased credits come after them.
- Included usage resets monthly, on the same day of the month your subscription started. Annual plans follow the same rule.
- Unused included usage does not roll over.
- Paid plans get an email at 90% of the included monthly usage. You can turn that email off.
- Free resets monthly from the day you signed up.
The old plans
Accounts still on the older Pro and Max plans have no dollar meter. Their usage API returns request counts only, and their limits are a five-hour session and a weekly window.
Our measurements on those accounts: the five-hour session runs in fixed blocks that end at minute :55, not in a rolling window. We checked six boundaries in August 2026 and saw no drift. The weekly window is fixed at seven days, and one reset landed exactly seven days after the one before it.
Ollama removed the quota percentages from the usage API on about 7 Oct 2026, so the checker estimates them. Calibration: about 0.10% of a session per request (two independent measurements, 0.103 and 0.093), and 64.9% weekly at 3,672 requests on a dashboard reading from 8 Oct 2026, mostly glm-5.3-flash traffic.
Moving from an old plan
Switching from an old Pro or Max plan to a new one resets usage. The session and weekly limits of the old plans no longer apply after the switch. The reset date stays on the subscription’s original start date.
How to tell which plan you are on
- Read the usage. A new-plan account gets usage_usd, input tokens, cached input tokens and output tokens in each bucket. An old-plan account gets request_count only.
- Read the plan. The account endpoint, POST /api/me, returns the plan name, for example pro.
- Or paste the key on the home page. The checker shows EXACT monthly dollars for a new plan and EST. session and weekly windows for an old one.
What our test account showed
On a new-plan Pro account, calls stopped at exactly $60.00 of cumulative usage. From then on they returned 429 until the monthly reset. The full message is in When capped.
Check the real numbers
Paste an Ollama Cloud key on the home page. Exact monthly dollars on new plans, estimates on old ones, nothing stored.
Check your own usage