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

# Estimated Savings

> Compare eligible serverless usage at public list prices with what the same tokens would have cost on Claude Opus 5.5.

The Savings view estimates how much your account saved by using Fireworks models and Nexus Auto, compared with serving the same tokens entirely on the baseline model.

Savings covers eligible direct Fireworks serverless usage and usage sent through Nexus Auto. It counts Nexus Auto turns that went to a closed model, not only turns that went to an open model.

To view your savings, go to Analytics → [Savings](https://app.fireworks.ai/account/usage?type=savings).

![Analytics Savings tab showing total saved this month, cache hit rate, and a Spend vs Opus 5.5 chart with per-day stacked bars and a baseline line](https://mintcdn.com/fireworksai-docs/1tZ4fm2ZdJDIJQkk/images/fireworks-nexus/savings/savings-view.png?fit=max\&auto=format\&n=1tZ4fm2ZdJDIJQkk\&q=85\&s=1d6661029e720801ca778cf4bcbf742c)

The Savings view, with example data.

> [!NOTE]
>
> Only account admins on Nexus-enabled accounts can view Estimated Savings.

## How savings are calculated

For each comparable token category, Fireworks calculates:

```text theme={null}
Estimated savings = baseline cost − actual cost at public list price
Savings rate = estimated savings ÷ baseline cost
```

| Amount | Meaning |
| - | - |
| **Actual cost** | Estimated cost of the models that served the requests, at public list prices. |
| **Baseline cost** | What the same uncached input, cached input, cache-write, and output tokens would have cost on Claude Opus 5.5. |
| **Estimated savings** | Baseline cost minus actual cost. Positive, zero, and negative values are all shown. |

The Savings view names the baseline model it compares against. Today that is Claude Opus 5.5. The baseline can change when the comparison is updated.

## How to read a result

| Result | What it means |
| - | - |
| **Positive** | The serving models cost less than Claude Opus 5.5 for the same tokens. |
| **Zero** | The usage cost the same as Claude Opus 5.5. Usage already served by Opus 5.5 usually saves nothing. |
| **Negative** | The serving model cost more than Claude Opus 5.5 would have. The amount is not rounded to zero. |

### Example

Suppose an account's eligible usage cost an estimated **\$2.45** at public list prices. The same tokens would have cost an estimated **\$8.15** on Claude Opus 5.5.

```text theme={null}
Estimated savings = $8.15 − $2.45 = $5.70
Savings rate = $5.70 ÷ $8.15 = 69.9%
```

The Savings view reports **\$5.70** in estimated savings, or **69.9%**. These amounts are illustrative.

## What is included

Savings includes eligible serverless inference usage recorded for the account:

* Fireworks-hosted serverless models
* Closed models called through Nexus Auto
* Direct eligible Fireworks serverless requests
* Priced uncached input, cached input, cache-write, and output tokens

When you group usage by user or model, usage without a recorded user or model appears as unattributed. Internal variants of a Fireworks-hosted model are grouped under its public model where possible.

## What is not included

Savings does not include:

* Dedicated deployment usage
* Token categories without both an actual price and a baseline price
* Unpriced token quantities
* Discounts, credits, taxes, negotiated rates, or other invoice adjustments

Groups with no comparable priced usage are omitted.

## Savings are estimates

> [!WARNING]
>
> Savings figures are for comparison, not invoice amounts. Actual cost uses public list prices, not your account's contracted pricing. Closed-model provider costs are estimates too, and can differ from the provider's invoice. For Fireworks billing totals, use the Costs view or your billing statement. Recent usage can take a while to appear in Savings.

## Related

* [Nexus Auto](https://fireworks.ai/docs/nexus/auto.md)
* [Effort](https://fireworks.ai/docs/nexus/orchestration-preferences.md)
* [Usage and Cost](https://fireworks.ai/docs/nexus/metrics.md)
* [Spend Limits](https://fireworks.ai/docs/nexus/usage-limits.md)
* [Provider Keys](https://fireworks.ai/docs/nexus/provider-keys.md)


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