> ## Documentation Index
> Fetch the complete documentation index at: https://docs.caveman.so/llms.txt
> Use this file to discover all available pages before exploring further.

# Caveman Cloud billing: plans, usage pricing, and limits

> How Caveman Cloud bills: plans, free monthly allowances, graduated usage tiers for events, agent runs, and routing, packages, billing limits, and included AI credits.

Caveman Cloud bills for usage of its own products, not for seats or for your model traffic. Each metered product has a free monthly allowance, graduated prices past it, and an optional billing limit so you never pay more than you choose. Manage everything on the **Billing** page.

<Note>
  Your model provider bill (OpenAI, Anthropic, Google, and others) is separate and paid to the provider. Control that spend with [Budgets](/governance/budgets) and [per-key limits](/governance/api-keys#per-key-limits).
</Note>

## Plans

| Plan | Card required | Usage beyond the free allowance |
| - | - | - |
| **Free** | No | Not available. Each product stops at its free allowance until the month resets. |
| **Pay-as-you-go** | Yes | Billed monthly on graduated tiers, up to the billing limit you set |
| **Enterprise** | No | Billed by contract. The Billing page shows usage only. |

There is no per-seat charge. Usage resets on the first of each month, UTC.

## Metered products

| Product | Unit | Free each month |
| - | - | - |
| **LLM observability** | Event | 100,000 events |
| **Agent runs** | Minute | 600 minutes |
| **Routing** | Decision | 100,000 decisions |

Pricing is graduated: each unit is priced at the rate of the tier it falls in, so only usage above a threshold gets that tier's price.

<AccordionGroup>
  <Accordion title="LLM observability (per event)">
    | Events per month | Price per event |
    | - | - |
    | First 100,000 | Free |
    | 100,001 to 150,000 | \$0.00035 |
    | 150,001 to 250,000 | \$0.000175 |
    | 250,001 to 500,000 | \$0.0001 |
    | 500,001 to 1,000,000 | \$0.00008 |
    | 1,000,001 to 10,000,000 | \$0.00007 |
    | 10,000,001 to 50,000,000 | \$0.000065 |
    | Above 50,000,000 | \$0.00006 |
  </Accordion>

  <Accordion title="Agent runs (per minute)">
    | Minutes per month | Price per minute |
    | - | - |
    | First 600 | Free |
    | 601 to 10,000 | \$0.012 |
    | 10,001 to 100,000 | \$0.01 |
    | Above 100,000 | \$0.008 |
  </Accordion>

  <Accordion title="Routing (per decision)">
    | Decisions per month | Price per decision |
    | - | - |
    | First 100,000 | Free |
    | 100,001 to 2,000,000 | \$0.0001 |
    | 2,000,001 to 10,000,000 | \$0.000045 |
    | 10,000,001 to 50,000,000 | \$0.000025 |
    | Above 50,000,000 | \$0.00001 |
  </Accordion>
</AccordionGroup>

The Billing page always shows the current tier table for each product, so treat it as the source of truth if these figures change.

## Read your usage

On Pay-as-you-go, the top of the page shows:

* **This month**: charges so far in the current period.
* **Projected**: this month's usage carried to month end at the same pace, priced on each product's tiers.

Each product card shows usage against its free allowance, this month's and projected charges, its billing limit, and its tier table.

## Set billing limits

A billing limit is a dollar ceiling per product for the month.

<Steps>
  <Step title="Open Billing">
    Find the product card you want to cap.
  </Step>

  <Step title="Edit the billing limit">
    Enter a dollar amount, or choose no limit. Agent runs start with a default limit of \$150.
  </Step>

  <Step title="Save">
    Save the limit. The card shows the new ceiling immediately.
  </Step>
</Steps>

When a product reaches its limit, that product pauses until the period resets: **Recording paused** for LLM observability, **New runs paused** for agent runs. Raise the limit to resume sooner. On the Free plan, each product stops at its free allowance.

<Warning>
  Pausing observability means new traffic is not recorded, which also affects spend reports and savings evidence for that period. Set observability limits with headroom.
</Warning>

## Packages

Packages add governance and identity features on top of your plan.

| Package | Price | Adds |
| - | - | - |
| **Boost** | \$250 / month | Project access control, audit log export |
| **Scale** | \$750 / month | Everything in Boost, plus SSO (OIDC and SAML), Require SSO, IdP group mappings |
| **Enterprise** | Contract | Everything in Scale, plus SCIM provisioning |

Add or remove Boost and Scale on the Billing page. If you remove a package, controls you already configured stay in place, but you cannot create new ones that need the package. For Enterprise, contact Caveman from the Billing page.

## Your included AI

Every user gets a monthly AI credit allowance (currently \$10) for Caveman's built-in agents and automatic model decisions. It is personal and shared across all organizations you belong to, valued at catalog list prices, and renews monthly.

* **AI credits remaining** and **AI credits used** show your balance. In-flight requests reserve credits until their cost is known.
* Caveman uses Luna for routine work and Sol for complex tasks.
* When credits run out, Caveman's AI work pauses. Your own application traffic is unaffected and keeps using your provider billing.

## Who can manage billing

Owners, Admins, and Billing contacts can read billing. Only **Owners** and **Billing** contacts can add a card, open **Manage billing**, set limits, or change packages. If a payment fails, the Billing page shows a past-due notice while the charge is retried; update the card in **Manage billing** before the subscription cancels.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.