Ollama Cloud limits
Ollama Cloud's $0 entry plan is Pay as you go, with no subscription and 3 concurrent requests. Paid plans include a fixed amount of usage credits each month — $60 on Pro ($20/mo or $200/yr), $300 on Max ($100/mo) — metered in tokens, at each model's published per-million-token rate for input, cached input and output, and included usage on paid plans resets monthly with no rollover. Pay as you go pays per request with usage credits. Concurrency is 3 on Pay as you go, 3 on Pro, 10 on Max, and 10 on Team.
Full detail below — plan tiers, concurrency, per-model rates, resets and what legacy plans still do. Figures are re-read from ollama.com/pricing every day and were last verified . For token-per-minute or request-per-minute limits, see the rate limits section below.
Concurrency limits
Each plan limits how many cloud requests can be in-flight at once. Requests over the limit are queued; once the queue fills, additional requests are rejected until a slot opens.
| Plan | Concurrent requests | Included credits / month | Price |
|---|---|---|---|
| Pay as you go | 3 | — | $0 |
| Pro | 3 | $60 | $20/mo or $200/yr |
| Max | 10 | $300 | $100/mo |
| Team (Early access) | 10 | $1,000 | $500/mo |
| Enterprise | — | — | Custom |
How is Ollama Cloud usage measured, and when does it reset?
Usage is metered in tokens, at each model's published per-million-token rate for input, cached input and output. There is no fixed token cap: a request on a model with a high per-token rate spends your credits faster than the same request on a cheap one.
- Monthly reset — included credits on Pro, Max and Team refresh monthly on the same day of the month your subscription started, including on annual plans.
- No rollover — unused included usage is replaced at the reset, not carried forward.
- Extra usage — every plan, including Pay as you go, can buy usage credits. On paid plans included credits are spent first, then the purchased balance.
An email alert fires at 90% of the included monthly usage on paid plans (it can be turned off in settings).
Which models use credits fastest?
Every cloud model has its own rate per million input, cached-input and output tokens. A few examples; the full model pricing table is on the pricing page. — means no published rate, not zero. Clef is an input-only decision model, not an autoregressive text generator; no output tariff or output-token ceiling is published.
These are the standard rates. Peak pricing applies between 12:00 and 18:00 UTC, Monday to Friday. A few models bill higher inside it — see peak pricing.
| Model | Input / 1M | Cached input / 1M | Output / 1M |
|---|---|---|---|
| clef | $0.24 | — | — |
| glm-5.3 | $1.4 | $0.26 | $4.4 |
| gpt-oss:20b | $0.07 | $0.035 | $0.3 |
| kimi-k3 | $3 | $0.3 | $15 |
Legacy Pro and Max plans: session and weekly limits
On those plans the two rolling windows are a session limit that resets every 5 hours and a weekly limit that resets every 7 days. This site's own Pro key is on such a plan — see how limits affect benchmark numbers.
Rate limits (RPM / TPM / context)
Ollama Cloud does not publicly list requests-per-minute (RPM), tokens-per-minute (TPM), or maximum context window sizes on its pricing page as of . The only usage constraints published there are the concurrency limits and the credit-based usage allowance above.
If you need exact rate limit numbers for production planning:
- Check ollama.com/pricing — limits may have been added since this page was last updated.
- Check the Ollama Cloud documentation for any new constraints.
- Contact Ollama at hello@ollama.com for Team and Enterprise details.
Model deprecation schedule
Ollama Cloud deprecates cloud models with advance notice via email and the website. The following models were announced for retirement on June 16, 2026:
| Retiring model | Replacement |
|---|---|
| kimi-k2-thinking | kimi-k2.6 |
| kimi-k2:1t | kimi-k2.6 |
| minimax-m2 | minimax-m3 |
| glm-4.6 | glm-5.1 |
| qwen3-next:80b | qwen3.5 |
| qwen3-vl:235b | qwen3.5 |
| qwen3-vl:235b-instruct | qwen3.5 |
| cogito-2.1:671b | deepseek-v4-flash |
Deprecations only affect cloud models. Local models are not affected. Source: docs.ollama.com/cloud.
How limits affect benchmark numbers
This site shows both Ollama Cloud Pro and Free benchmark rows. The Pro key is a legacy subscription taken out before the credits-based plans, so its cadence is not budget-constrained: Pro rows are sampled about every 10 minutes. Free rows are sampled about every 60 minutes so the free-tier allowance lasts across the supported models.
Benchmarks run sequentially (one request at a time) so concurrency limits do not affect our measurements. Usage allowances can affect data freshness — especially on the free tier, where the worker intentionally spaces runs out to avoid exhausting the allowance early.
See the full methodology for details, including how circuit-breaker logic and rate-limit backoff work.
Frequently asked questions
Is Ollama Cloud free?
Ollama Cloud has a $0 entry plan, Pay as you go: no subscription, 3 concurrent requests, and usage paid per request with usage credits. Paid plans are Pro at $20/mo or $200/yr for 3 concurrent requests and $60 of monthly credits, and Max at $100/mo for 10 concurrent requests and $300. Running Ollama locally on your own hardware is always free and unlimited.
What are Ollama Cloud's usage limits?
Paid plans include a fixed amount of usage credits per month — $60 on Pro, $300 on Max, $1,000 shared on Team — metered in tokens, at each model's published per-million-token rate for input, cached input and output. Credits reset monthly on the same day of the month your subscription started, including on annual plans and do not roll over. Ollama emails paid accounts at 90% of the included usage, and every plan can add extra credits.
How many requests can I run at once on Ollama Cloud?
Pay as you go runs 3 concurrent requests, Pro runs 3 concurrent requests, Max runs 10 concurrent requests, and Team runs 10 concurrent requests. Requests beyond your plan's concurrency limit are queued rather than rejected; once the queue is full, further requests are rejected until a slot frees up.
Does Ollama Cloud still have a 5-hour session limit and a weekly limit?
Only on legacy plans. Pro and Max subscriptions started before the credits-based plans keep their original terms — a usage allowance with a session limit that resets every 5 hours and a weekly limit that resets every 7 days — until the subscriber switches. Switching grants the new plan's full monthly credits immediately and removes the session and weekly windows; the reset date stays on the original subscription date.
How much does an Ollama Cloud team plan cost?
Team is $500/mo with unlimited users and $1,000 of usage credits per month shared across the team, plus 10 concurrent requests, centralized billing and priority support. Usage beyond the included credits draws from a shared team balance billed as you go. Enterprise pricing is custom.