350+ Tools CoveredSource Data Updated Weeklydates

Ollama Pricing: Free Local Runtime, Cloud Plans from $0 to $500/mo

By Egor Burlakov · Edited · Source dates below

Buying snapshot

Scroll sideways to see all columns. With a keyboard, focus this table and use the arrow keys.

Decision pointWhat Ollama states

License

The Ollama repository on GitHub is published under the MIT license.

Local use

Running models on your own hardware is always unlimited; the $0 Pay as you go plan includes running models locally.

Installation

Install script for macOS and Linux, a PowerShell script for Windows, manual downloads, and the official ollama/ollama Docker image on Docker Hub.

Cloud billing unit

Tokens, at each model's input, cached input and output price per million tokens.

Cloud hosting and data

Models are hosted primarily in the United States, with possible routing to Europe for extra capacity. Prompt or response data is never logged or trained on; hosting partners must have no-logging, no-training and zero data retention policies.

Which plan fits

The main cost differences between plans are the monthly fee, the included usage credits and how many cloud requests can run at once. Model access and team features also differ; the next table lists them.

Scroll sideways to see all columns. With a keyboard, focus this table and use the arrow keys.

Ollama plans, prices and limits as shown on the Ollama pricing page

PlanPublished priceIncluded usage creditsConcurrent requestsOllama's stated fit

Pay as you go

$0, no subscription

None included; pays per token for every cloud model

3

Local models, plus cloud models paid per token

Pro

$20/mo, or $200/yr billed annually ($16.67/mo billed annually)

$60 per month

3

Shorter, well-defined day-to-day tasks

Max

$100/mo

$300 per month

10

Power users who run multiple agents simultaneously

Team (early access)

$500/mo, unlimited users

$1,000 per month, shared across the team

10

Teams scaling with open models

Enterprise

Custom; contact Ollama

Volume usage pricing

Everything in Team

Larger teams with volume usage

What each plan includes

Scroll sideways to see all columns. With a keyboard, focus this table and use the arrow keys.

Plan inclusions as listed on the Ollama pricing page

PlanWhat it adds

Pay as you go

Run models locally; no subscription; no service fees.

Pro

Everything in Pay as you go, plus access to larger pro models. Fast mode is marked "coming soon".

Max

Everything in Pro, plus early access to the newest models.

Team

Everything in Pro, plus centralized billing and administration and priority support. Shared projects, skills and instructions are marked "coming soon".

Enterprise

Everything in Team, plus model access controls (limit team access to specific models), cost budgets for users and API keys, a private Slack channel with dedicated support, and custom security questionnaires.

How cloud usage is billed

Every plan, including Pay as you go, can buy usage credits. Ollama spends included plan credits first, then draws from the purchased credit balance. On Pro, Max and Team, included usage resets monthly on the day your subscription started, including on annual plans. On Team, usage beyond the included credits draws from one shared team balance billed as you go; you can add a set amount to that balance and turn off automatic usage billing.

Scroll sideways to see all columns. With a keyboard, focus this table and use the arrow keys.

Selected cloud model rates from the Ollama pricing page, $ per million tokens

ModelInputCached inputOutput

gpt-oss:20b

$0.07

$0.035

$0.30

gpt-oss:120b

$0.15

$0.014

$0.60

gemma4

$0.14

$0.05

$0.40

deepseek-v4.1-flash

$0.30

$0.006

$1.20

deepseek-v4.1-flash (Off-Peak)

$0.15

$0.003

$0.60

deepseek-v4-pro

$1.32

$0.044

$3.96

deepseek-v4-pro (Off-Peak)

$0.66

$0.022

$1.98

mistral-large-4

$0.70

$0.07

$2.10

glm-5.3

$1.40

$0.26

$4.40

kimi-k3

$3.00

$0.30

$15.00

What drives the cloud bill

  • Time of day. Some models carry a separate Off-Peak rate. Ollama states off-peak pricing applies "outside 12:00 and 18:00 UTC on weekdays and all day on weekends".

  • Parallel work. Requests beyond your plan's concurrency limit are queued until a slot opens. The queue has a fixed limit; when it is full, new requests are rejected. Running several agents at once is what moves a buyer from 3 to 10 concurrent requests.

Conditions that are easy to miss

  • Included credits do not roll over. The included amount refreshes at each monthly reset, so unused credit is lost.

  • Usage alert. On paid plans, Ollama emails a reminder at 90% of your included monthly usage; you can turn it off in settings.

  • Switching from an older Pro or Max plan. Usage is reset and the new plan's full monthly amount is available at once. The old plans' session and weekly limits no longer apply, and the reset date stays on the original subscription start date.

  • One account per person. Joining a Team creates a separate team account that you switch to with the same login.

Our take

For cloud use, pick a plan by the parallel work you need, not by the credits alone: if your agents need more than three requests running at once, the choice starts at Max; if several people need one shared balance and central billing, it starts at Team.

Evaluate this price

Sources