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

# Billing, usage, and limits

> Distinguish session concurrency, custom avatar slots, included usage, overage, and invoice status when planning an Anam integration.

Use your organization's [Billing and usage](https://lab.anam.ai/subscription) page and agreement for its current allowance and rates. The [pricing page](https://anam.ai/pricing) describes current public plans; an organization's effective limits can also reflect its contract or approved overrides.

## Session concurrency

All websites using the same organization share its simultaneous-session allowance.

The [concurrency endpoint](/docs/api-reference/sessions/get-current-concurrency-status) returns an approximate active count, the limit, and an estimated wait. It is an advisory snapshot, not a reservation: another request can use capacity before your start request arrives, and stale session state can affect the estimate. Session creation remains authoritative and can reject a start even after a successful pre-check.

A rejected start does not guarantee that a session was created. Check the returned error before retrying: a `429` can reflect an organization limit, service capacity, or a spend limit, not just a need to upgrade. Show the reason to the user and avoid retrying in a tight loop. Counts of rejected attempts can include repeated requests from the same person; they are not counts of unique customers or lost revenue.

## Custom avatars and creation requests

Each saved, non-deleted custom avatar in your organization occupies a custom avatar slot. Lab and the API check this count before creating another avatar. Finishing generation or ending a conversation does not free a slot.

An allowance describes the limit, not the number of custom avatars currently saved. Check actual slot usage separately before concluding how much capacity remains.

If creation is blocked because all custom avatar slots are occupied, waiting for a running conversation to finish will not free one. Review unused avatars or contact Anam Support about the effective limit. Check for personas using an avatar before deleting it.

The limits and counts measure different things:

* **Session concurrency:** simultaneous sessions using the organization's session allowance.
* **Custom avatar slot usage:** saved, non-deleted custom avatars counted by the creation gate, not a count of avatars currently speaking.
* **Creation admission:** whether a new request passes slot, feature-access, image-generation, and moderation checks. A free slot does not guarantee admission.
* **Avatar inventory:** the assets visible in a catalog can include stock avatars and other categories, so a catalog total is not automatically custom slot usage.
* **Generated-video job concurrency:** a separate limit for script-to-video jobs, not an avatar inventory count.

## Included and used minutes

For example, **0 of 250 included minutes** means zero minutes used out of 250 included for the displayed billing period. It does not mean that the allowance is exhausted. This is an example of the display, not a promise that a particular plan includes 250 minutes.

Included minutes are an allowance, used minutes are measured consumption, and overage is billable use beyond that allowance where your plan or agreement permits it. Overage eligibility, spend caps, and maximum session duration are separate controls. An active subscription does not by itself establish that another session is allowed.

Anam records session duration in seconds and uses that duration for minute-based usage. Silence, a muted microphone, or an idle avatar does not pause an otherwise active session. Close sessions when they are no longer needed. The server-reported session duration is used for usage accounting; calling a browser method alone is not proof that billable streaming has started.

## Bringing your own LLM or TTS

Anam charges depend on your agreement and the components used by the session. Audio passthrough uses Anam's avatar service while your external LLM and TTS providers may charge separately. This does not by itself establish a discount or final invoice amount.

The aggregate session-minute allowance is not calculated by adding avatar, voice, LLM, and STT minutes together. A minute of a session remains a minute of aggregate usage even when several Anam components run during it.

## Subscription and invoice status

Subscription status describes the subscription lifecycle. Invoice status describes a particular invoice's payment state. An **active** subscription does not establish that every invoice is paid; check the relevant invoice in your billing records.

During billing migrations, older invoices can remain with the previous billing system. Use the invoice and agreement for the period in question rather than applying a current plan's rates retroactively. Contact Anam Support to confirm account-specific overage, discounts, or negotiated terms.