# Ollama Cloud pricing and limits

> Machine-readable reference maintained by Ollama TPS (https://ollamatps.com), an
> independent live benchmark of Ollama Cloud model speed. **We are not Ollama.**
> These are Ollama's published plan terms, republished here in a parseable form.
> Source: https://ollama.com/pricing — verified 2026-09-06 (re-read daily by an automated sync).
> Always confirm at the source; plans and limits change without notice.

## Plans

### Free
- Price: $0
- Concurrent requests: 1
- Usage: starter usage credits, starter models only — add credits to unlock every model
- Positioning: For getting started with open models

### Pro
- Price: $20/mo or $200/yr
- Concurrent requests: 3
- Usage: $60 of usage credits per month
- Positioning: For shorter, well-defined day-to-day tasks

### Max
- Price: $100/mo
- Concurrent requests: 10
- Usage: $300 of usage credits per month
- Positioning: For power users who run multiple agents simultaneously

### Team (Early access)
- Price: $500/mo
- Concurrent requests: 10
- Usage: $1,000 of usage credits per month, shared across the team
- Positioning: For teams scaling with open models

### Enterprise
- Price: Custom
- Concurrent requests: not published
- Usage: volume usage pricing
- Positioning: For larger teams with volume usage pricing

## How usage is metered

- Metered by tokens, at each model's published per-million-token rate for input, cached input and output.
- Paid plans include a fixed dollar amount of usage credits each month; Free includes a starter amount for a smaller set of starter models.
- Every plan, including Free, can add extra usage credits. Included credits are spent first, then the extra balance. Adding credits on Free unlocks every model.
- Ollama emails the account owner at 90% of the included monthly usage (paid plans; can be turned off).

## Model pricing (USD per million tokens)

| Model | Input | Cached input | Output |
|---|---|---|---|
| deepseek-v4-flash | $0.22 | $0.007 | $0.66 |
| deepseek-v4-pro | $0.66 | $0.022 | $1.98 |
| gemma4 | $0.14 | $0.05 | $0.4 |
| glm-5.3 | $1.4 | $0.26 | $4.4 |
| glm-5.3-flash | $0.15 | $0.03 | $0.5 |
| glm-5.2 | $1.4 | $0.26 | $4.4 |
| glm-5.1 | $1 | $0.2 | $3.2 |
| gpt-oss:120b | $0.15 | $0.014 | $0.6 |
| gpt-oss:20b | $0.07 | $0.035 | $0.3 |
| kimi-k3 | $3 | $0.3 | $15 |
| kimi-k2.7-code | $0.95 | $0.19 | $4 |
| kimi-k2.6 | $0.95 | $0.16 | $4 |
| minimax-m3 | $0.6 | $0.12 | $2.4 |
| minimax-m2.7 | $0.3 | $0.06 | $1.2 |
| mistral-large-3 | $0.5 | — | $1.5 |
| nemotron-3-nano | $0.06 | — | $0.24 |
| nemotron-3-super | $0.015 | $0.015 | $0.6 |
| nemotron-3-ultra | $0.1 | $0.1 | $3 |
| qwen3.5:397b | $0.6 | — | $3.6 |

`—` means no cached-input tier is published for that model. It is not zero.

### Peak pricing

Peak pricing applies between 12:00 and 18:00 UTC, Monday to Friday. Models absent from this table bill at the standard rate around the clock.

| Model | Input | Cached input | Output |
|---|---|---|---|
| deepseek-v4-flash | $0.44 | $0.014 | $1.32 |
| deepseek-v4-pro | $1.32 | $0.044 | $3.96 |

## Reset windows

- Included usage resets **monthly**, on the same day of the month your subscription started, including on annual plans. Free resets monthly from the date you signed up.
- Unused included usage does **not** roll over; the included amount refreshes at each reset.
- **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.

## Concurrency behaviour

- Requests beyond the plan's concurrent-request limit are **queued**, not rejected.
- The queue has a fixed depth; once full, further requests are rejected until a slot frees.

## Running locally

Running Ollama on your own hardware is free and unlimited. The plans above govern
cloud inference only.

## Related

- Ollama Cloud speed leaderboard (live, updated ~every 10 minutes): https://ollamatps.com/
- Full limits explainer: https://ollamatps.com/limits/
- Pricing explainer: https://ollamatps.com/pricing/
- How speed is measured: https://ollamatps.com/methodology/
- Multi-provider comparison (Ollama vs OpenCode Zen vs OpenCode Go): https://tokendyno.com/