> For the complete documentation index, see [llms.txt](https://burp-ai-agent.six2dez.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://burp-ai-agent.six2dez.com/backends/nvidia-nim.md).

# NVIDIA NIM

NVIDIA NIM (`integrate.api.nvidia.com`) hosts a range of open and proprietary models behind an OpenAI-compatible chat-completions interface. The extension targets `/v1/chat/completions` with the configured bearer token.

## Requirements

* An NVIDIA Developer account and an API key (starts with `nvapi-…`).
* Network access to `integrate.api.nvidia.com`.

## Setup

1. Sign up at [build.nvidia.com](https://build.nvidia.com/) and generate an API key.
2. Pick a model (for example `moonshotai/kimi-k2.5`).
3. Configure the backend in the **AI Backend** settings tab.

## Configuration

| Setting               | Default                            | Description                                                             |
| --------------------- | ---------------------------------- | ----------------------------------------------------------------------- |
| **Preferred Backend** | `nvidia-nim`                       | Select backend.                                                         |
| **Base URL**          | `https://integrate.api.nvidia.com` | NVIDIA-hosted endpoint; override only when targeting a self-hosted NIM. |
| **Model**             | *(empty)*                          | Model identifier, e.g. `moonshotai/kimi-k2.5`.                          |
| **API Key**           | *(empty)*                          | Your `nvapi-…` token. Sent as `Authorization: Bearer …`.                |
| **Extra Headers**     | *(empty)*                          | Optional extra `Header: value` lines if a gateway requires them.        |
| **Timeout**           | `120`                              | Request timeout in seconds.                                             |

A working baseline:

```
Backend: NVIDIA NIM
Base URL: https://integrate.api.nvidia.com
Model: moonshotai/kimi-k2.5
API Key: nvapi-...
```

## Health Check Traffic

The NVIDIA NIM health check is a free `GET /v1/models` against the configured Base URL, with the API key as a bearer token, sent through Burp's networking (the same Montoya transport as chat and scanner requests), so Burp's upstream proxy settings apply to it. It contains no captured Burp context and is visible in Proxy history. It runs no billed completion. It runs on the same schedule as every remote provider: in the BApp Store build only on demand (Save, a backend change, a pill click, or a chat reply); in the GitHub full build at startup, after a settings or backend change and on a pill click, never on a timer. Like every AI request, it is refused while Burp's "Use AI" gate refuses the backend (see [Which Build?](https://burp-ai-agent.six2dez.com/getting-started/which-build.md)).

## Response Delivery Limitation

Normal NIM requests currently include `stream: true`, but the production Montoya transport buffers the response and the shared parser expects one JSON document before calling the UI once. It does not decode SSE `data:` frames. If the selected NIM endpoint honors streaming strictly, the response may fail JSON parsing; the current implementation should not be described as functional token-by-token streaming.

## Privacy Considerations

NVIDIA NIM is a cloud backend. The same privacy guidance as other cloud providers applies:

* Keep privacy mode at `STRICT` or `BALANCED` (the default) for real targets.
* Review the context preview dialog before sending auto-captured traffic.
* Review the [Privacy Modes](https://burp-ai-agent.six2dez.com/privacy-and-logging/privacy-modes.md) page for redaction patterns.

## Output Token Limits

The extension sets `max_tokens` automatically per request type:

| Request Type                 | `max_tokens` |
| ---------------------------- | ------------ |
| **Chat**                     | 4096         |
| **Scanner (single request)** | 2048         |
| **Scanner (batch analysis)** | 4096         |
| **Payload generation**       | 1024         |

## Troubleshooting

{% hint style="info" %}

* `401 Unauthorized`: verify the API key is a valid `nvapi-…` token and not expired.
* `404 Not Found` on the model: confirm the model ID exactly matches NVIDIA's catalog.
* Slow first token: NIM models are shared; cold starts are expected.
* Extra headers: only add them if your organization routes requests through a gateway.
  {% endhint %}

## Retry Behavior

Classified transient transport exceptions trigger up to 6 total attempts with five possible delays (`500 / 1000 / 1500 / 2000 / 3000 ms`). HTTP error responses are not retried inside the same call, although 429/5xx responses count toward the connection's circuit breaker. Each actual retry is recorded in the [AI Request Logger](https://burp-ai-agent.six2dez.com/privacy-and-logging/ai-request-logger.md) as a `RETRY` activity.

## Related Pages

* [Backends Overview](https://burp-ai-agent.six2dez.com/backends/overview.md)
* [Generic (OpenAI-compatible)](https://burp-ai-agent.six2dez.com/backends/openai-compatible.md)
* [Troubleshooting](https://burp-ai-agent.six2dez.com/reference/troubleshooting.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://burp-ai-agent.six2dez.com/backends/nvidia-nim.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
