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

# Adding Pricing Adjustments

> Learn how to apply discount or markup multipliers to a Prisma AIRS AI Gateway Integration so cost tracking reflects your effective rate with a provider.

Pricing Adjustments let you apply a discount or markup to an Integration, so cost tracking reflects your effective rate with that provider. A multiplier of `1` leaves pricing unchanged. `0.8` applies a 20% discount. `1.2` applies a 20% markup.

> [!NOTE]
>
> Requires:
>
> * Gateway version **2.7.0** or higher

This is especially useful for:

* **Negotiated Discounts**: Reflect contract pricing or committed-use rates from a provider on the corresponding Integration.
* **Internal Cost Showback**: Apply a markup so the cost reported to internal teams or workspaces includes your platform overhead.
* **Custom Per-Integration Rates**: Maintain different effective pricing across multiple Integrations of the same provider (e.g. a discounted production Integration alongside a standard-rate sandbox).

## Adding Pricing Adjustments to an Integration

You can configure Pricing Adjustments directly from Strata Cloud Manager, in the **Basic Integration Details** step.

1. Navigate to the relevant [**Integration**](https://stratacloudmanager.paloaltonetworks.com/) in your Strata Cloud Manager account, and create a new Integration or open an existing one.
2. On the **Integration Details** step, toggle **Pricing Adjustments** on.
3. Choose a **Multiplier** mode:
   * **Default**: Quick form for the most common token types.
   * **Custom**: JSON editor for the full multiplier shape, including reasoning, audio, image, and additional units.
4. Enter your multipliers. Empty fields inherit from `Default`.
5. Save the Integration.

> [!TIP]
>
> For a discount, convert the percentage to a multiplier with:
>
> `multiplier = 1 - (discount% / 100)`
>
> Example: a 10% discount on `Default` and a 15% discount on `Request Tokens`:
>
> * `Default` → `1 - (10 / 100) = 0.90`
> * `Request Tokens` → `1 - (15 / 100) = 0.85`
>
> `Request Tokens` use `0.85`; `Response Tokens`, `Cache Read Tokens`, and `Cache Write Tokens` inherit `0.90` from `Default`.

### Configuration Fields

Default mode exposes the five most common multipliers:

> **Default**
>
> Multiplier applied to every token type unless a more specific multiplier is set below. A flat 20% discount across the Integration is just `0.8` here.

> **Request Tokens**
>
> Multiplier applied to input/request token cost.

> **Response Tokens**
>
> Multiplier applied to output/response token cost.

> **Cache Read Tokens**
>
> Multiplier applied to cache-read input token cost.

> **Cache Write Tokens**
>
> Multiplier applied to cache-write input token cost.

For other token types — reasoning, audio/image/text variants, image generation, or per-unit charges like `web_search` — switch to **Custom** mode and provide a JSON object with the keys you want to adjust:

```json theme={"system"}
{
  "multiplier": {
    "default": 0.8,
    "request_token": 0.7,
    "response_token": 0.9,
    "reasoning_token": 0.5,
    "image": { "default": 0.9 },
    "additional_units": { "web_search": 0.7 }
  }
}
```

The multiplier keys mirror the pricing keys in [AI Gateway Models](https://docs.portkey.ai/docs/aigw/product/model-catalog/gateway-models.md) — the open-source pricing database backing the AI Gateway's cost tracking. Any key present in a model's `pay_as_you_go` (or in `additional_units`) can be adjusted here.

> **Full multiplier reference**
>
> | Field | Applies to |
> | - | - |
> | `default` | Every token type unless a more specific multiplier is set |
> | `request_token` / `response_token` | Standard input and output tokens |
> | `cache_read_input_token` / `cache_write_input_token` | Prompt cache reads and writes |
> | `reasoning_token` | Reasoning/thinking tokens |
> | `request_audio_token` / `response_audio_token` / `cache_read_audio_input_token` | Audio modality tokens |
> | `request_text_token` / `response_text_token` / `cache_*_text_input_token` | Text-modality breakdowns where the provider reports them separately |
> | `request_image_token` / `response_image_token` / `cache_*_image_input_token` | Image-modality breakdowns |
> | `prediction_accepted_token` / `prediction_rejected_token` | Predicted-output tokens |
> | `image.default` | Per-image generation pricing across all qualities and sizes |
> | `additional_units.<key>` | Per-unit charges such as `web_search`, `file_search`, `input_image`, `input_video_standard`. See [Additional Units Reference](https://docs.portkey.ai/docs/aigw/product/model-catalog/gateway-models.md#additional-units-reference). |

## Per-Model Pricing Adjustments

Adjustments can also be set on an individual model within an Integration, using the same `pricing_adjustments` shape. This is useful when a negotiated rate applies to only part of a provider's catalog — for example a committed-use discount on one model family while the rest of the Integration bills at list price.

> [!NOTE]
>
> Per-model adjustments require Gateway version **2.22.0** or higher.

A model-level adjustment **fully replaces** the Integration-level one for that model — the two are not merged key by key. If a model defines `pricing_adjustments`, every multiplier for requests to that model comes from the model-level object, and any keys it omits fall back to `default` within that same object rather than to the Integration-level adjustment.

> [!WARNING]
>
> Because the replacement is whole-object, an Integration-level 20% discount does **not** carry over to a model that sets its own adjustment. Repeat any multipliers you still want, including `default`.

Models without their own `pricing_adjustments` continue to use the Integration-level adjustment.

> [!NOTE]
>
> If a model has its own custom pricing, that price is billed exactly as written — pricing adjustments set at the **model level or the Integration level are ignored** for that model. Other models in the same Integration are unaffected. To discount or mark up a custom-priced model, build the adjustment into the custom price itself.

## Setting Pricing Adjustments via the API

You can also configure Pricing Adjustments programmatically through the [Integrations API](https://docs.portkey.ai/docs/aigw/api-reference/integrations/post-integrations.md). Pass `pricing_adjustments` when creating or updating an Integration. Send `null` to clear all adjustments.

**cURL**

```bash theme={"system"}
curl -X PUT https://aigw.portkey.ai/v2/integrations/{integrationId} \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_PORTKEY_API_KEY" \
  -d '{
    "pricing_adjustments": {
      "multiplier": {
        "default": 0.8,
        "cache_read_input_token": 0.9,
        "cache_write_input_token": 0.9
      }
    }
  }'
```

**Python**

```python theme={"system"}
import requests

requests.put(
    "https://aigw.portkey.ai/v2/integrations/{integrationId}",
    headers={"Authorization": "Bearer YOUR_PORTKEY_API_KEY"},
    json={
        "pricing_adjustments": {
            "multiplier": {
                "default": 0.8,
                "cache_read_input_token": 0.9,
                "cache_write_input_token": 0.9,
            }
        }
    },
)
```

Once saved, the AI Gateway applies the multipliers to the base pricing for every subsequent request through this Integration, and the adjusted cost flows into logs, analytics, and budget tracking.


## Related topics

- [Adding Custom Models](https://docs.portkey.ai/docs/aigw/product/model-catalog/custom-models.md)
- [Put integrations by slug](https://docs.portkey.ai/docs/aigw/api-reference/integrations/put-integrations-by-slug.md)
- [Post integrations](https://docs.portkey.ai/docs/aigw/api-reference/integrations/post-integrations.md)
- [Model Pricing and Cost Management](https://docs.portkey.ai/docs/aigw/product/observability/cost-management.md)
- [Get integrations by slug](https://docs.portkey.ai/docs/aigw/api-reference/integrations/get-integrations-by-slug.md)


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