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

# View Usage and Billing

> Learn how to check your API usage and understand billing details

## What is Usage and Billing?

Every API call consumes quota and generates a billing record. This guide shows where to see your usage and how charges are calculated.

<Info>
  Quota is checked before each request. If your balance is insufficient, the request is rejected. See [Limits and Prerequisites](/features/model-router/others/limits-and-prerequisites) for more details.
</Info>

## How Quota Works

Model Router uses a two-phase quota system:

1. **Pre-deduction**: before your request is processed, the system checks and reserves quota
2. **Settlement**: after the request completes, you're charged based on actual usage; failed requests roll back the reservation

<Frame>
  <img className="rounded-xl" src="https://mintcdn.com/datacloud-924043c1/pEDy58oBG5CxVCQs/images/model-router/quota-flow.png?fit=max&auto=format&n=pEDy58oBG5CxVCQs&q=85&s=ea9d1a753cc7b1191b36266605f41b2a" alt="Quota check and settlement behavior" style={{ width: "100%", height: "auto" }} width="2410" height="1066" data-path="images/model-router/quota-flow.png" />
</Frame>

<Info>
  You're only charged for successful requests based on actual token usage.
</Info>

## Where to Look in the Console

All usage and billing views live under **Billing** in the [console](https://app.memorylake.ai/panel/billing) sidebar:

| Tab          | What you'll find                                                                      |
| ------------ | ------------------------------------------------------------------------------------- |
| **Overview** | Current balance, credits, and recent consumption at a glance                          |
| **Credits**  | Balance management and top-ups                                                        |
| **Usage**    | Aggregated product usage — separate views for MemoryLake Memory and MemoryLake Router |
| **Logs**     | Per-request records: model, tokens, latency, and cost details                         |
| **Payments** | Payment history and invoices                                                          |

In team spaces, team-wide statistics (member rankings, consumption trends, model usage) are on the team's **Stats** tab — see [Team Collaboration](/features/team-collaboration/quota-and-usage).

## Viewing Individual Call Billing

1. Open **Billing → Logs**
2. Click any call to see its details:
   * **Input/Output pricing**: cost per token
   * **Conversion process**: how the charge was calculated
   * **Actual deducted quota**: what was consumed
   * **Quota source**: personal, team, or mixed

<Frame>
  <img className="rounded-xl" src="https://mintcdn.com/datacloud-924043c1/pEDy58oBG5CxVCQs/images/model-router/billing-list.png?fit=max&auto=format&n=pEDy58oBG5CxVCQs&q=85&s=6aae8d2019d28cda466b51e020bcdcae" alt="Billing list in call logs" style={{ width: "100%", height: "auto" }} width="2512" height="1646" data-path="images/model-router/billing-list.png" />
</Frame>

<Frame>
  <img className="rounded-xl" src="https://mintcdn.com/datacloud-924043c1/pEDy58oBG5CxVCQs/images/model-router/billing-detail.png?fit=max&auto=format&n=pEDy58oBG5CxVCQs&q=85&s=5b863d359553000442cad7843fbaf854" alt="Billing details in call log details" style={{ width: "100%", height: "auto" }} width="1754" height="1624" data-path="images/model-router/billing-detail.png" />
</Frame>

## Understanding Billing Details

* **Input tokens**: cost for tokens you send to the model
* **Output tokens**: cost for tokens the model generates
* **Total cost**: input + output
* **Quota sources**: personal quota, shared team quota, or a mix — validated according to your current space context

## Model Pricing

View per-model pricing on the [Available Models page](https://app.memorylake.ai/panel/models/available) in the console. Pricing shown there is reference metadata; actual charges are calculated at settlement from real usage.

## Important Notes

1. **Quota limits**: requests are rejected when balance is insufficient — top up in **Billing → Credits** before sustained workloads.
2. **Context matters**: personal and team contexts draw on different quota pools; check your current space before automating.
3. **Real-time updates**: usage statistics update as you make calls.

## Troubleshooting

### "Insufficient Quota" Error

1. Check your balance in **Billing → Overview**
2. Top up credits, or ask your team admin for a larger member quota
3. Verify you're in the intended space (personal vs. team)

### Unexpected Charges

1. Open the call in **Billing → Logs**
2. Review input/output token counts and the conversion detail
3. Compare against the model's pricing on the Available Models page

## Related Documentation

* [List Available Models](/features/model-router/list-available-models)
* [Limits and Prerequisites](/features/model-router/others/limits-and-prerequisites)
* [Error Handling](/features/model-router/others/error-handling)
* [Team Collaboration — Quotas and Usage](/features/team-collaboration/quota-and-usage)