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

# LLM API Billing Rules Explained

Dear novita AI users,

This notice clarifies our LLM API billing policy, with a focus on how disconnected requests (HTTP 499) are handled.

## Pricing

novita AI LLM API is billed per token:

* **Input Tokens** — tokens consumed by the prompt
* **Output Tokens** — tokens generated by the model

Total Cost = Input Tokens × Input Rate + Output Tokens × Output Rate

Model-specific rates are available on the [Pricing Page](https://novita.ai/pricing).

## Billing Conditions

Charges apply when the model has begun inference. Requests that do not reach the model are not charged.

| Scenario                                                      | Charged | Reason                                         |
| :------------------------------------------------------------ | :------ | :--------------------------------------------- |
| Successful request (200)                                      | Yes     | Model completed inference                      |
| Client disconnected (499)                                     | Yes     | Model had begun inference                      |
| Invalid request / auth failure / rate limit (400/401/403/429) | No      | Request rejected before reaching the model     |
| Error due to platform issues (500/503/504)                    | No      | Infrastructure error; absorbed by the platform |

Full status code reference: [Error Codes](/docs/guides/error).

## 499 (Client Disconnected)

When a request reaches the model, inference starts immediately. If the client disconnects mid-request, the compute resources already consumed are still billable.

| Request Mode  | Billing                                                        |
| :------------ | :------------------------------------------------------------- |
| Non-Streaming | Charged for actual token usage regardless of disconnect timing |
| Streaming     | Charged for actual token usage regardless of disconnect timing |

This policy is consistent with standard industry practice across major LLM providers.

## Recommendations

1. **Set `max_tokens`** to control output length at the request level
2. **Configure client timeout ≥ 60s** to prevent unintended disconnections
3. **Select appropriate models** based on task requirements to optimize cost

## FAQ

<AccordionGroup>
  <Accordion title="Why am I charged if I disconnected before receiving a response?">
    Inference begins upon request arrival. Disconnecting does not stop computation already in progress.
  </Accordion>

  <Accordion title="How can I avoid 499 charges?">
    Use the `max_tokens` parameter to cap output length before sending the request.
  </Accordion>

  <Accordion title="Where do 499 charges appear in my account?">
    In the usage dashboard, listed alongside standard requests with actual token consumption.
  </Accordion>
</AccordionGroup>

For further questions, please contact our support team.

**The novita AI Team**