# β‘ Quantization
**Quantization** allows requests to be routed to **quantized endpoints**, which may deliver **faster inference** and **lower costs**, with a slight reduction in accuracy**.**
Because quantization affects inference behavior, this setting gives you explicit control over the model version used. You may choose to disable this feature to retain the original model for precision-critical tasks or regulatory compliance.
> π‘ **Note:** Quantized endpoints follow the same **security** and **data retention** as non-quantized endpoints.
## Via Web Console
1. Go to your [**Project Settings**](https://cortecs.ai/userArea/userProfile) **β Inference Section**.
2. Toggle **Allow Quantization** **ON** β to allow **routing** to quantized endpoints.
3. Toggle **OFF** β to restrict routing to **non-quantized endpoints only**.
## Via API
You can also control quantization directly in your requests using the `allow_quantization` parameter:
```json
{
"model": "devstral-2512",
"messages": [...],
"allow_quantization": true
}
```
* `true` β *(default)* β Quantized endpoints are allowed
* `false` β β Only non-quantized endpoints are used
For **project-wide enforcement**, you can also configure this setting via the [**Project Config API**](https://docs.cortecs.ai/advanced-usage/project-configuration/update-project-config), ensuring all team requests follow the same policy. π’
## When to use Quantization
* Reduce latency for real-time or high-throughput workloads
* Lower inference costs at scale
* Accept small accuracy trade-offs in exchange for performance gains
## Compliance Focus
* Quantized and non-quantized endpoints are **GDPR compliant**
* Data is **never used for model training**
* Quantization alters inference behavior, which may impact EU AI Act conformity assessments. Disable this setting if strict adherence to the original model behavior is required.
