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

# Mira managed pricing

> Plan, metering, entitlement and cost-of-goods model for the managed multi-tenant Mira channel product.

**Status:** plan names and prices approved (see [decisions](#decisions)).
Billing is not enabled: the add-ons enter the `packages/payment-core`
versioned pricing catalog in a later slice, and until then no checkout,
invoice or entitlement path sells them. Runtime design is in
[Mira cloud channels](https://docs.tuturuuu.com/platform/ai/mira-cloud-channels.md).

## Decisions

| Decision | Scope | Default | Exceptions |
| - | - | - | - |
| **Plans:** Mira Business at $99 and Mira Business Plus at $199 per seat per month, as in [plan shape](#plan-shape). | Workspace add-ons for managed Mira on every official channel. | Not sold until the catalog slice ships. | Tuturuuu's internal tenant is not billed. |
| **At quota, managed keys charge overage.** Usage past the pooled quota is billed as metered overage instead of stopping. | Managed-key replies of every paying tenant. | Overage on; the tenant's daily and monthly spend caps and the durable stop fence remain the hard ceiling the tenant sets. | A tenant may pick throttle instead; a reached cap still sets the `cap` stop. |
| **BYOK carries a small platform fee.** | Replies answered with the tenant's own OpenAI, Anthropic or Google key. | Fee per BYOK reply, metered with the other usage. | BYOK replies never draw down the managed reply quota. |

Approved amounts, metered in integer micro-USD per settled turn:

| Charge | Rate | Micro-USD per unit |
| - | - | - |
| Managed overage | \$8 per 1,000 weighted replies | 8,000 per weighted reply |
| BYOK platform fee | \$1 per 1,000 BYOK replies | 1,000 per BYOK reply |

Billing stays off until the catalog slice ships; until then the runtime
records the meters and the cost in micro-USD
(`mira_usage_daily.cost_micro_usd` and `weighted_replies`) and bills nothing.

## Plan shape

Mira managed is a **workspace add-on billed per seat**, not a renamed personal
plan. The personal catalog (`d301a-personal-v1`) already uses the name Pro for
a $19.99 personal plan, and the approved workspace prices list Pro at $19 a
month;
a $100–$200 Mira tier under the same name would collide in checkout, receipts
and entitlements.

| Add-on | Price per seat per month | Preset | Included per seat (pooled across the workspace) | Channels per workspace |
| - | - | - | - | - |
| Mira Business | \$99 | `fast` (quality available, counted ×8) | 4,000 replies, 20,000 triaged messages | 3 |
| Mira Business Plus | \$199 | `quality` | 6,000 quality replies or 48,000 fast replies, 60,000 triaged messages | 10, plus bring-your-own Discord bot |

* **Seat:** a workspace member who can operate Mira (configure, receive
  escalations, reply as a human from the Tuturuuu chat mirror). People who
  only message Mira on a channel are not seats.
* **Requires:** an active workspace plan; the add-on attaches to it.
* **Annual:** ten months' price, matching the existing catalog convention.
* **BYOK:** both add-ons accept the tenant's own OpenAI, Anthropic or Google
  key. Replies on BYOK do not draw down the reply quota and carry the BYOK
  platform fee; channel count, triage volume and fair-use rate limits still
  apply. No seat discount, because infrastructure, support and channel
  onboarding costs remain.

## Metering

Settled per turn by the tenant object and flushed to `mira_usage_daily`
through the work Queue.

| Meter | Unit | Used for |
| - | - | - |
| `mira.reply` | replied turn, weighted by preset (fast 1, quality 8) | quota and overage |
| `mira.triage` | triaged inbound message | quota and abuse signal |
| `mira.tokens` | input, cached input and output tokens per model | cost and margin reporting |
| `mira.channel` | connected channel-day | channel limit |
| `mira.whatsapp_service` | delivered WhatsApp service message per number | informational; Meta bills the tenant's WhatsApp Business Account directly after its free tier |

Managed-key usage is also recorded in the existing AI credits ledger so one
source reports workspace AI spend.

## Quotas, overage and throttling

* At 80 % of the pooled reply quota the workspace's Mira managers are
  notified.
* At 100 %, the tenant's choice applies: **overage** (default) at the
  managed overage rate up to the tenant's monthly spend cap, or
  **throttle** (replies fall back to the `fast` preset, then to "a person
  will get back to you" with escalation).
* The tenant's daily spend cap and the durable stop fence apply regardless of
  plan headroom.

## Entitlements

`mira_tenants.plan_snapshot` holds the add-on, seat count, quotas and period,
refreshed from the billing provider readback (never client checkout data).
The tenant object checks it before every turn:

| Entitlement | Business | Business Plus |
| - | - | - |
| Discord shared bot, WhatsApp Cloud, Zalo OA / Bot | yes | yes |
| Bring-your-own Discord bot | no | yes |
| Quality preset | counted ×8 | default |
| Knowledge sources | 50 documents | 500 documents |
| Per-person rules | yes | yes |
| Analytics retention | 30 days | 13 months |
| Support | standard | priority, 99.9 % SLA credit |

Loss of the add-on (cancel, failed payment past grace) sets the tenant stop
fence; config and history are kept for 30 days for reactivation.

## Cost of goods

### Assumptions

A **turn** is one replied message. Input averages 3,000 tokens of which 2,000
are a cached stable prefix; output averages 150 tokens. Triage uses about
600 input and 20 output tokens on the cheap tier. Cloudflare operations per
inbound message: one ingress request, three object requests, about ten SQLite
row writes and one Queue message with three operations.

Prompt-cache hits are assumed on 60 % of turns (low-traffic tenants miss the
cache window), with cache writes at the provider's write multiplier, and a 30 %
token allowance for newer tokenizers. List prices per million tokens (input /
cached input / output), checked 2026-11-21; re-verify before catalog approval,
because providers change them (Gemini 3.8 Flash doubles on 2027-01-01):

| Tier | Model | Price |
| - | - | - |
| Fast | Claude Haiku 5.5 | $0.10 / $0.01 / \$0.50 |
| Fast | gpt-6-luna | $0.10 / $0.01 / \$0.50 |
| Fast | Gemini 3.5 Flash-Lite | $0.30 / $0.03 / \$2.50 |
| Quality | Claude Sonnet 5.5 | $2.00 / $0.10 / \$10.00 |
| Quality | gpt-6.2-sol | $2.00 / $0.10 / \$10.00 |
| Quality | Gemini 3.1 Pro | $2.00 / $0.20 / \$12.00 |

### Per-unit cost

| Unit | Cost |
| - | - |
| Fast reply (Haiku 5.5 or gpt-6-luna) | about \$0.0004 |
| Quality reply (Sonnet 5.5 or gpt-6.2-sol) | about \$0.0075 |
| Triage | about \$0.0001 |
| Cloudflare per inbound message | about \$0.00002 |
| Shared Discord gateway, per shard | about \$4 per month, spread across tenants |
| WhatsApp and Zalo provider charges | billed by the provider to the tenant |

### Per tenant per month (one seat)

| Profile | Volume | LLM | Cloudflare | Payment fees | Total COGS | Price | Gross margin |
| - | - | - | - | - | - | - | - |
| Business, typical | 1,500 fast replies, 8,000 triaged | \$1.40 | \$0.20 | \$4.40 | about \$6.00 | \$99 | about 94 % |
| Business, at quota | 4,000 fast replies, 20,000 triaged | \$3.60 | \$0.50 | \$4.40 | about \$8.50 | \$99 | about 91 % |
| Business Plus, typical | 2,500 quality replies, 20,000 triaged | \$20.75 | \$0.50 | \$8.40 | about \$29.70 | \$199 | about 85 % |
| Business Plus, at quota | 6,000 quality replies, 60,000 triaged | \$51.00 | \$1.50 | \$8.40 | about \$61 | \$199 | about 69 % |

Payment fees assume about 4 % plus $0.40 per charge. Support, Meta and Zalo
onboarding, and on-call are fixed costs outside COGS. Overage at $8 per 1,000
weighted replies is more than eight times the model cost of a weighted reply
on either preset, so overage never erodes margin.

### Tuturuuu's own Mira

The internal tenant at today's volume and at ten times that volume is
estimated in the [Mira cloud channels cost model](https://docs.tuturuuu.com/platform/ai/mira-cloud-channels.md#cost-model).

## Open decisions

1. Price of personal-account mode for opted-in paying tenants, including the
   per-account `SessionContainer` (about \$8 per account per month on the
   `basic` class); see
   [personal opt-in](https://docs.tuturuuu.com/platform/ai/mira-cloud-channels.md#personal-account-opt-in-paying-tenants).
2. Seat definition with the billing owners and the `packages/payment-core`
   catalog shape for a workspace add-on.


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