# Welcome

Analyse HTTP traffic in Burp Suite Professional with your choice of model provider.

BurpGPT Pro brings AI analysis directly into Burp Suite Professional. Use local models through Ollama, connect a compatible self-hosted endpoint, or choose a [supported hosted provider](/getting-started/supported-model-providers), including Anthropic, Google AI Gemini, Mistral AI, and OpenAI. OpenAI-compatible APIs can be local, self-hosted, or hosted by another provider.

Choose one of three workflows:

* **Targeted analysis:** Select one or more HTTP requests and responses for separate analyses using your scanner prompt.
* **Active scanning:** Add AI scan checks to Burp's active scans.
* **AI Chat:** Ask follow-up questions in the `AI Chat` request-editor tab, with optional request and response context.

The extension supports security testing workflows where model output helps guide manual validation. AI-generated insights can be incomplete or inaccurate, so verify the evidence before reporting a finding.

{% hint style="info" %}
Third-party model-provider usage costs are not included. Cloud provider API accounts, keys, quotas, and billing are managed separately with the selected provider.
{% endhint %}

Start with [Quick start](/getting-started/quick-start) for the shortest path to a working setup, or go directly to [Installation](/getting-started/installation) if you are loading the extension for the first time.


# Quick start

Set up BurpGPT Pro and complete your first targeted analysis.

Connect a model provider and run your first targeted analysis. You can add active scan checks or use AI Chat once this setup works.

## Before you start

Make sure you have:

* Burp Suite Professional 2026.7 or later.
* The BurpGPT Pro JAR file.
* Your licence key.
* Either a cloud provider API key or a local/self-hosted provider endpoint.
* A captured HTTP request and response to analyse in Burp.

## 1. Load the extension

1. Open Burp Suite Professional.
2. Go to `Extensions` → `Installed`.
3. Click `Add`.
4. Select `Java` as the extension type, choose the JAR file, and click `Next`.
5. Confirm that the `BurpGPT Pro` menu appears.

For the full installation guide, see [Installation](/getting-started/installation).

## 2. Activate your licence

Open `BurpGPT Pro` → `Licence`, then activate your licence with the key from your purchase email.

{% hint style="warning" %}
Each successful `Activate` uses an activation, even on the same computer. Used activations cannot be recovered. If your licence is already saved, use `Refresh` instead. See [Activate your licence](/getting-started/activate-your-licence).
{% endhint %}

## 3. Configure a model provider

Open the `BurpGPT Pro` tab and select `Provider settings`, then choose a setup guide:

* For hosted APIs, see [Configure a hosted provider](/model-setup/use-supported-cloud-based-model-providers).
* For Ollama or self-hosted endpoints, see [Local models and compatible endpoints](/model-setup/use-supported-local-model-providers).

Enter the provider, base URL, API key if required, model name, timeout, and request parameters. Model names in the dropdown are examples, not a list fetched from your provider. Press Enter after typing a custom model identifier.

## 4. Test the provider

Click `Test request` and confirm that it succeeds before analysing traffic.

If the test fails, check Burp's `Logger` tab for the provider request and response. See [Test your provider](/model-setup/test-and-validate-model-provider-settings) for details.

## 5. Analyse a request

1. Open `AI scanner` and review the role and prompt. Start with the `user` role and a prompt containing `{REQUEST}` and `{RESPONSE}`.
2. Select a captured request in `Proxy` → `HTTP history`.
3. Right-click and select `Extensions` → `BurpGPT Pro` → `Scan with AI (results in Target → Site map)`.

You do not need to enable `Scan: On` for targeted analysis. You can also select multiple requests; each is analysed separately.

## 6. Review the output

Open `Target` → `Site map` and select the analysed request. A successful analysis creates an issue named **GPT-generated insights**, with **Information** severity and **Tentative** confidence. Open it to review the analysis alongside the HTTP exchange.

Always manually validate AI-generated results before relying on them in a security report.

## Next steps

* [Analyse HTTP traffic](/analysis-and-prompts/analyse-http-traffic) in batches or during active scans.
* [Use AI Chat](/analysis-and-prompts/use-ai-chat) to investigate with follow-up questions.
* [Use the prompt library](/analysis-and-prompts/use-the-prompt-library) to save and reuse your instructions.

If no issue appears, follow [Scans do not produce results](/help-and-faq/troubleshooting#scans-do-not-produce-results).


# Installation

Install BurpGPT Pro in Burp Suite Professional.

## Prerequisites

* [Burp Suite Professional](https://portswigger.net/burp/pro) **2026.7 or later** for BurpGPT Pro 3.1.
* Java **21 or later** if you launch Burp with an external Java runtime.
* The BurpGPT Pro JAR file provided with your purchase.
* Your BurpGPT Pro licence key.

Burp Suite's native installer includes its own Java runtime. A separate JDK is not required to install the extension.

## Load the extension

1. Open Burp Suite and select `Extensions` → `Installed`.
2. Click `Add`.
3. Select `Java` as the extension type and browse to your BurpGPT Pro `.jar` file.
4. Click `Next` and confirm that the extension loads without errors.
5. Open `BurpGPT Pro` → `Licence` and [activate your licence](/getting-started/activate-your-licence).

Then follow the [quick start](/getting-started/quick-start) to configure a provider and run your first analysis.

## Upgrade to 3.1

Replace the existing extension with the new JAR. Version 3.1 requires Burp Suite Professional 2026.7 or later.

Provider and scanner settings reset to defaults on upgrade from earlier releases. Re-enter your provider configuration, run `Test request`, and check the scanner prompt and scan preference before use. Saved licences and prompt libraries are retained.

To load the updated example prompts, export your custom prompts before [resetting the prompt library](/analysis-and-prompts/use-the-prompt-library#restore-the-bundled-examples).


# Activate your licence

Activate your BurpGPT Pro licence or refresh its displayed status.

BurpGPT Pro features are available after your licence is active. If the licence dialog does not open automatically after loading the extension, open it from `BurpGPT Pro` → `Licence`.

## Activate a licence

{% hint style="warning" %}
Each successful `Activate` consumes an activation, even on the same computer. **Used activations cannot be recovered.** To check an existing saved licence, use `Refresh` instead.
{% endhint %}

1. Open `BurpGPT Pro` → `Licence`.
2. Paste your licence key into the `Licence key` field.
3. Click `Activate`.
4. Confirm that `Status` changes to `Activated`.

After activation, the `BurpGPT Pro` tab, context-menu scan action, and `AI Chat` editor are available in Burp Suite.

## Refresh licence status

Use `Refresh` when you need to update the displayed licence status, validity dates, activation count, or licensed email.

`Refresh` is available once a licence has been saved. It checks the saved licence without consuming another activation. If the status is `Verification failed`, use `Refresh` to retry verification.

The licence dialog shows:

| Field         | Meaning                                    |
| ------------- | ------------------------------------------ |
| `Status`      | Current licence state.                     |
| `Licensed to` | Email address associated with the licence. |
| `Order ID`    | Order identifier for the licence.          |
| `Activations` | Used and allowed activations.              |
| `Expires`     | Licence expiry date.                       |

If activation or refresh fails, check the extension's `Errors` tab under `Extensions` → `Installed`. HTTP failures include a status code, such as `HTTP 404`. See [Why did licence activation fail?](/help-and-faq/faq/what-are-the-possible-causes-for-an-unsuccessful-activation-of-my-burpgpt-pro).


# Supported model providers

Choose a hosted, local, or self-hosted model provider and review shared request parameters.

Open the `BurpGPT Pro` tab and select `Provider settings` to choose a provider. The same configuration is used for scanning and AI Chat.

Provider, model, and scanner settings are saved in Burp's user preferences and reused across projects. The [prompt library](/analysis-and-prompts/use-the-prompt-library) belongs to the current project instead. Review the active provider and scanner prompt when switching engagements.

## Cloud-based providers

| Provider         | Documentation                                                       |
| ---------------- | ------------------------------------------------------------------- |
| Anthropic        | [Anthropic API documentation](https://docs.anthropic.com/en/home)   |
| Google AI Gemini | [Gemini API documentation](https://ai.google.dev/gemini-api/docs)   |
| Mistral AI       | [Mistral documentation](https://docs.mistral.ai/)                   |
| OpenAI           | [OpenAI API documentation](https://developers.openai.com/api/docs/) |

Cloud providers receive the prompts and traffic you submit. Check their data-handling policies and API access requirements before use. Provider usage is billed separately from BurpGPT Pro.

Follow the [cloud provider setup guide](/model-setup/use-supported-cloud-based-model-providers).

## Local and self-hosted providers

* **Ollama:** Connect to an Ollama server through its native API. See [Ollama setup](/model-setup/use-supported-local-model-providers/with-the-ollama-provider).
* **OpenAI-compatible API:** Connect to an endpoint that supports OpenAI-compatible chat completions. See [OpenAI-compatible setup](/model-setup/use-supported-local-model-providers/with-openai-compatible-api).

Local processing depends on the endpoint and model runtime you choose. Confirm that your deployment does not forward requests to a cloud service if data must remain on your infrastructure.

Run `Test request` after configuring any provider.

When you switch providers, a custom `Base URL` is retained. Review it before testing; clearing the field uses the selected provider's default where one exists. `OpenAI-compatible API` always requires an explicit base URL.

On `Provider settings`, `Manage global settings` → `Reset to defaults` resets the provider and model configuration. It leaves the scanner prompt, scan toggle, and project prompt library unchanged.

## Request parameters

The `Request parameters` editor accepts the following fields for hosted, local, and self-hosted providers. Use this reference with any provider setup guide.

| Parameter           | Value type       |
| ------------------- | ---------------- |
| `temperature`       | Number           |
| `top_p`             | Number           |
| `top_k`             | Integer          |
| `max_tokens`        | Integer          |
| `frequency_penalty` | Number           |
| `presence_penalty`  | Number           |
| `stop`              | Array of strings |

For example:

```json
{
  "temperature": 0.2,
  "max_tokens": 1024
}
```

Use `{}` to leave the parameters unspecified. Unknown field names and invalid value types are highlighted in the editor. Supported parameters and valid ranges vary by provider and model; confirm them in your provider's documentation, then run `Test request`.

Settings save as you edit. An invalid JSON draft leaves the previous saved parameter object in use. A syntactically valid object can still be saved with unsupported fields or types, so fix highlighted errors before testing, scanning, or chatting.

`max_tokens` limits generated output; it does not truncate the HTTP traffic or prompt sent to the model. Use narrower [placeholders](/analysis-and-prompts/use-placeholder-reference) if the input exceeds your model's context limit.


# Configure a hosted provider

Configure a hosted model provider and validate its settings.

You need API access and sufficient quota with your chosen provider. Provider accounts and usage fees are managed separately from your BurpGPT Pro subscription.

{% hint style="warning" %}
Prompts, selected HTTP traffic, and chat messages are sent to the configured provider. Review its data-handling and retention policies before submitting sensitive information.
{% endhint %}

## Configure the provider

1. Open the `BurpGPT Pro` tab and select `Provider settings`.
2. Choose a [supported cloud provider](/getting-started/supported-model-providers#cloud-based-providers) from `Model provider`.
3. Enter your provider's `API key`.
4. Leave `Base URL` at its default unless your deployment uses a different endpoint.
5. Select or enter an exact `Model` identifier available to your account. The dropdown contains illustrative examples, not a fetched list of available models. Press Enter to apply a typed identifier.
6. Set `Read timeout` in seconds. A value of `0` disables the response timeout.
7. Configure `Request parameters` using the [shared reference](/getting-started/supported-model-providers#request-parameters).
8. Click `Test request` to check the configuration.

Provider settings are shared by targeted analysis, active scanning, and AI Chat. Set the scanner's message role and prompt separately in `AI scanner`.

## Request parameters

See the shared [request-parameter reference](/getting-started/supported-model-providers#request-parameters) for supported fields, examples, and validation guidance.

See [Troubleshooting](/help-and-faq/troubleshooting) if the test fails.

Next, [analyse HTTP traffic](/analysis-and-prompts/analyse-http-traffic) or [use AI Chat](/analysis-and-prompts/use-ai-chat).


# Local models and compatible endpoints

Choose Ollama or an OpenAI-compatible API for your model endpoint.

Choose the integration that matches your model server:

* [Ollama](/model-setup/use-supported-local-model-providers/with-the-ollama-provider) for Ollama's native API.
* [OpenAI-compatible API](/model-setup/use-supported-local-model-providers/with-openai-compatible-api) for endpoints that support OpenAI-compatible chat completions.

Both integrations can connect to a model server on your machine or another host. An OpenAI-compatible endpoint can also be operated by a hosted provider; API compatibility does not determine where data is processed.

BurpGPT Pro sends selected traffic, prompts, and chat messages to the configured endpoint. To keep model processing on infrastructure you control, check that the endpoint and model runtime do not forward requests to a cloud service.

After configuration, run `Test request` in `Provider settings` before scanning or using AI Chat.


# Configure Ollama

Connect BurpGPT Pro to a local Ollama model.

[Install Ollama](https://ollama.com/download), download the model you want to use, and ensure the Ollama server is running. See the [Ollama CLI reference](https://docs.ollama.com/cli) for model and server management.

## Configure the provider

1. Open the `BurpGPT Pro` tab and select `Provider settings`.
2. Select `Ollama` from `Model provider`.
3. Use `http://localhost:11434` as `Base URL`, or enter the address of your Ollama server. Do not append `/api/chat`.
4. Leave `API key` blank for a standard local installation.
5. Enter the exact name of a downloaded model in `Model` and press Enter to apply it. The dropdown contains examples; it does not list installed models. To list models, run:

   ```sh
   ollama ls
   ```
6. Set `Read timeout` in seconds. Local models may need longer to load and respond.
7. Use `{}` for `Request parameters`, or add fields from the extension's [supported parameter list](/getting-started/supported-model-providers#request-parameters). Not every Ollama option is exposed by the extension.
8. Click `Test request` before scanning or using AI Chat.

{% hint style="info" %}
For local processing, use a local model. Ollama can also use cloud models, so a localhost endpoint alone does not guarantee that your model processes data locally. Check your Ollama configuration and model choice.
{% endhint %}

Next, [analyse HTTP traffic](/analysis-and-prompts/analyse-http-traffic) or [use AI Chat](/analysis-and-prompts/use-ai-chat).


# Configure an OpenAI-compatible API

Connect to a model endpoint that supports OpenAI-compatible chat completions.

Use `OpenAI-compatible API` for a local, self-hosted, or third-party endpoint that supports the OpenAI chat completions schema.

Before you start, have the endpoint's API base URL, model identifier, and API key if required. Confirm that the model server is reachable from the computer running Burp.

## Configure the provider

1. Open the `BurpGPT Pro` tab and select `Provider settings`.
2. Select `OpenAI-compatible API` from `Model provider`.
3. Enter the API `Base URL`, typically ending in `/v1`. Do not enter the full `/chat/completions` URL.
4. Enter an `API key` if the endpoint requires authentication.
5. Enter the exact `Model` identifier exposed by the endpoint and press Enter to apply it. The dropdown contains examples; it does not query the endpoint's model list.
6. Set `Read timeout` in seconds.
7. Configure `Request parameters` using the extension's [supported fields](/getting-started/supported-model-providers#request-parameters). Only include parameters accepted by your endpoint and model.
8. Click `Test request`.

The editor checks parameter names and value types. The endpoint determines whether a model exists and whether it supports those parameters. If the test fails, inspect the response in Burp's `Logger`.

Selected data is sent to the configured endpoint. An OpenAI-compatible API may be hosted locally or remotely; compatibility describes its API format, not its data-handling policy.

Next, [analyse HTTP traffic](/analysis-and-prompts/analyse-http-traffic) or [use AI Chat](/analysis-and-prompts/use-ai-chat).


# Test your provider

Check that your configured provider can answer a model request.

1. Open the `BurpGPT Pro` tab and select `Provider settings`.
2. Review the provider, base URL, API key, model, timeout, and request parameters.
3. Click `Test request`.
4. Review the result displayed in the dialog.

The test sends a model request using the same provider configuration as targeted analysis, active scanning, and AI Chat. It uses the role and prompt currently configured in `AI scanner`, with placeholders left as literal text. It does not attach the selected HTTP exchange or create a Burp issue. Any text you have written directly into that prompt is sent to the provider, and the request may incur provider usage charges.

A successful test confirms that the provider can respond to the test request. It does not guarantee that a larger scan prompt will fit the model's context limit or finish within the configured timeout.

If the test fails, inspect the request and response in Burp's `Logger`. Common causes include an incorrect model identifier, unsupported parameters, authentication failures, rate limits, insufficient quota, and connection problems.

See [Troubleshooting](/help-and-faq/troubleshooting) for the next checks.


# Use the prompt library

Create, edit, back up, and reuse scanner prompts.

Open the `BurpGPT Pro` tab and select `Prompt library` to manage saved prompts. Use the search field to find entries, then select a row to edit it or select multiple rows to remove them.

Changes to the library are saved automatically in the current Burp project file and restored when you reopen that project. Use export and import to reuse a library in another project. Provider and scanner settings are saved separately in Burp's user preferences.

{% hint style="warning" %}
In a temporary project, the library lasts only until you close Burp. Export prompts you want to keep before closing it.
{% endhint %}

## Add or edit a prompt

1. Click `Add`, or select one existing prompt and click `Edit`.
2. Enter the `Author`, `Category`, and `Prompt`. All three fields are required.
3. Click `OK` to save.

Scanner prompts can include placeholders such as `{REQUEST}`, `{RESPONSE}`, and `{URL}`. See the [placeholder reference](/analysis-and-prompts/use-placeholder-reference) for the complete list.

## Use a prompt for scanning

1. Right-click a prompt in the table.
2. Select `Send to AI scanner`.
3. Open `AI scanner` to review the prompt and message role before scanning.

This action copies the prompt text into the scanner settings. It leaves the message role unchanged and does not start a scan. Later library edits do not update the scanner prompt automatically; send the edited prompt again when you want to use it.

## Remove prompts

Select one or more rows and click `Remove`. Export a backup first if you may need the prompts later.

## Export the library

1. Click `Export`.
2. Choose a destination and save the file with a `.json` extension.

Export includes the entire library, regardless of the current table selection or search filter. You can continue using the interface while the file is saved.

## Import prompts

1. Click `Import`.
2. Select a previously exported JSON file.

Imports merge entries by `id`: an imported entry replaces an existing entry with the same ID. Entries with different IDs are kept, even when their text is identical. If a file contains the same ID more than once, the last entry is used.

A prompt library file is a JSON array. For example:

```json
[
  {
    "id": "efdecb60-64a7-40b1-ab59-cb342d11877b",
    "author": "Security team",
    "category": "authentication",
    "text": "Review this exchange for authentication weaknesses. Cite the evidence and suggest a validation step.\n\nRequest:\n{REQUEST}\n\nResponse:\n{RESPONSE}",
    "created": "2026-10-07T12:00:00Z"
  }
]
```

`author`, `category`, and `text` must contain non-blank values. When omitted, `id` and `created` are generated automatically. Preserve an entry's ID when you want a later import to update it.

## Restore the bundled examples

{% hint style="warning" %}
Resetting replaces the current library with the bundled examples. Export custom prompts first so you can import them again afterwards.
{% endhint %}

Open `Manage global settings` → `Reset to defaults` on the `Prompt library` page. Existing libraries are retained on upgrade, so reset the library if you want the updated 3.1 examples.


# Placeholder reference

Look up the placeholders available in scanner prompt templates.

Placeholders insert values from the HTTP exchange into scanner prompts. Open the `BurpGPT Pro` tab and select `Placeholder reference` to search the same list by name or description.

Use the tokens below in `AI scanner` prompts or in library prompts sent to the scanner. Names are case-sensitive. Unrecognised tokens remain unchanged; they are not custom variables. AI Chat does not expand scanner placeholders.

Unavailable response and timing values are empty. Use `{HAS_RESPONSE}` when the prompt needs to distinguish an absent response.

{% hint style="warning" %}
Placeholders insert data as supplied by Burp, without automatic redaction. Complete-message tokens include headers and bodies. Review the data you include; narrower tokens can limit the context sent to your provider.
{% endhint %}

## Complete messages

| Placeholder      | Value                                                     |
| ---------------- | --------------------------------------------------------- |
| `{REQUEST}`      | The complete scanned request.                             |
| `{RESPONSE}`     | The complete scanned response, or empty when unavailable. |
| `{HAS_RESPONSE}` | Whether the scan item has a response.                     |

## Target service

| Placeholder      | Value                                                |
| ---------------- | ---------------------------------------------------- |
| `{URL}`          | The complete request URL.                            |
| `{HTTP_SERVICE}` | The target HTTP service.                             |
| `{SCHEME}`       | The target URL scheme.                               |
| `{HOST}`         | The target hostname or IP address.                   |
| `{PORT}`         | The target port.                                     |
| `{SECURE}`       | Whether the target service uses a secure connection. |
| `{IP_ADDRESS}`   | The target host's dynamically resolved IP address.   |

## Request metadata

| Placeholder              | Value                                                               |
| ------------------------ | ------------------------------------------------------------------- |
| `{METHOD}`               | The HTTP request method.                                            |
| `{PATH}`                 | The request path, including its query string.                       |
| `{PATH_WITHOUT_QUERY}`   | The request path without its query string.                          |
| `{QUERY}`                | The request query string.                                           |
| `{FILE_EXTENSION}`       | The file extension in the request path.                             |
| `{REQUEST_HTTP_VERSION}` | The request HTTP version.                                           |
| `{REQUEST_CONTENT_TYPE}` | The request content type detected by Burp.                          |
| `{REQUEST_HEADERS}`      | The request headers, one per line.                                  |
| `{REQUEST_BODY}`         | The request body.                                                   |
| `{REQUEST_BODY_LENGTH}`  | The request body length in bytes.                                   |
| `{REQUEST_LENGTH}`       | The complete request length in bytes.                               |
| `{REQUEST_BODY_OFFSET}`  | The byte offset at which the request body starts.                   |
| `{REQUEST_PARAMETERS}`   | The request parameters parsed by Burp.                              |
| `{REQUEST_IN_SCOPE}`     | Whether the request URL is in Burp's target scope.                  |
| `{REQUEST_MARKERS}`      | The request marker ranges as start-inclusive/end-exclusive offsets. |

## Response metadata

| Placeholder                     | Value                                                                |
| ------------------------------- | -------------------------------------------------------------------- |
| `{STATUS_CODE}`                 | The response HTTP status code, or empty when unavailable.            |
| `{REASON_PHRASE}`               | The response HTTP reason phrase, or empty when unavailable.          |
| `{RESPONSE_HTTP_VERSION}`       | The response HTTP version, or empty when unavailable.                |
| `{RESPONSE_MIME_TYPE}`          | The response MIME type detected by Burp.                             |
| `{RESPONSE_STATED_MIME_TYPE}`   | The response MIME type stated in its headers.                        |
| `{RESPONSE_INFERRED_MIME_TYPE}` | The response MIME type inferred from its body.                       |
| `{RESPONSE_HEADERS}`            | The response headers, one per line.                                  |
| `{RESPONSE_BODY}`               | The response body, or empty when unavailable.                        |
| `{RESPONSE_BODY_LENGTH}`        | The response body length in bytes, or empty when unavailable.        |
| `{RESPONSE_LENGTH}`             | The complete response length in bytes, or empty when unavailable.    |
| `{RESPONSE_BODY_OFFSET}`        | The byte offset at which the response body starts.                   |
| `{RESPONSE_COOKIES}`            | The cookies set by the response.                                     |
| `{RESPONSE_ATTRIBUTES}`         | The response attributes calculated by Burp.                          |
| `{RESPONSE_MARKERS}`            | The response marker ranges as start-inclusive/end-exclusive offsets. |

## Burp metadata

| Placeholder              | Value                                                                  |
| ------------------------ | ---------------------------------------------------------------------- |
| `{ANNOTATION_NOTES}`     | The notes attached to the scan item.                                   |
| `{ANNOTATION_HIGHLIGHT}` | The highlight colour attached to the scan item.                        |
| `{REQUEST_SENT_AT}`      | The time at which Burp sent the request.                               |
| `{TIME_TO_FIRST_BYTE}`   | The duration from sending the request to receiving the response start. |
| `{TOTAL_RESPONSE_TIME}`  | The duration from sending the request to receiving the response end.   |

## Example

```
Review this exchange for security weaknesses. Separate observations from
hypotheses, cite supporting evidence, and suggest a validation step.

Method: {METHOD}
URL: {URL}
Response available: {HAS_RESPONSE}

Request:
{REQUEST}

Response:
{RESPONSE}
```

Use narrower placeholders when you only need part of the exchange. For example, `{REQUEST_HEADERS}` and `{RESPONSE_HEADERS}` avoid sending bodies when reviewing header configuration.


# Analyse HTTP traffic

Analyse HTTP traffic with targeted analysis, active scanning, or AI Chat.

Configure your model provider and confirm that `Test request` succeeds before analysing traffic. Provider requests and responses appear in Burp's `Logger`.

## Before you start

* [Activate your licence](/getting-started/activate-your-licence) and [test your provider](/model-setup/test-and-validate-model-provider-settings).
* Configure the role and prompt in `AI scanner` for both targeted analysis and active scans. Start with the `user` role; include [placeholders](/analysis-and-prompts/use-placeholder-reference) for the traffic you want analysed.
* For targeted analysis, capture or select the requests you want to review. For active scanning, have a Burp active scan ready to run.

## Active scanning

1. Open the `BurpGPT Pro` tab and select `AI scanner`.
2. Configure the message role and prompt template.
3. Enable scanning so the toggle displays `Scan: On`.
4. Start an active scan in Burp Suite.

{% hint style="info" %}
`Scan: On` enables AI checks for active scans; it does not start a scan or analyse every request in Proxy history. Automatic AI scanning is off by default.
{% endhint %}

The **LLM Vulnerability Analysis** check runs on a per-request basis. Burp's selected checks and scheduling determine whether and when it runs.

**Expected result:** Each completed AI analysis creates a **GPT-generated insights** issue in Burp. See [Review AI-generated insights](/analysis-and-prompts/view-gpt-generated-results).

Supported [placeholders](/analysis-and-prompts/use-placeholder-reference) are replaced with values from each HTTP exchange before the prompt is sent to the model. Turn the toggle off when you want active scans to run without AI analysis.

The scanner sends a single message. `Role` is case-insensitive: `system` sends a system message, `assistant` or `ai` sends an assistant message, and other values send a user message. Some providers reject particular roles or message arrangements; start with `user` and validate your configuration with `Test request`.

On the `AI scanner` page, `Manage global settings` → `Reset to defaults` restores the role and prompt only. It does not change `Scan: On` / `Scan: Off`; turn scanning off explicitly when needed.

## Targeted analysis

1. Select one or more requests in Burp Suite.
2. Right-click and choose `Extensions` → `BurpGPT Pro` → `Scan with AI (results in Target → Site map)`.
3. Review the generated issues in `Target` → `Site map`.

Targeted analysis uses the scanner's configured role and prompt. It is available even when the automatic scan toggle is off.

**Expected result:** A **GPT-generated insights** issue appears under each successfully analysed request in `Target` → `Site map`.

Requests in a selected batch are processed one after another. Each request and its available response get a separate model request and issue; the batch is not combined into one analysis. Results appear as each analysis completes. If one request fails, the failure is logged and the remaining selected requests are still processed.

## AI Chat

Select a request, open its `AI Chat` editor tab, and ask a question. Choose whether to include the request, response, or both with the next message. See [Use AI Chat](/analysis-and-prompts/use-ai-chat).

Scan results are [reported as Burp issues](/analysis-and-prompts/view-gpt-generated-results); chat responses appear in the chat history. Validate any suspected vulnerability before reporting it.


# Review AI-generated insights

Find and interpret AI-generated insights in Burp Suite.

Successful scan analyses create issues named **GPT-generated insights**, with **Information** severity and **Tentative** confidence. These labels are fixed by the extension, not assigned from the model's assessment. An issue is created even when the model reports no suspected vulnerability.

For targeted analysis, find the issue under the relevant request in `Target` → `Site map`. Active scan results are also reported through Burp's scanner.

Open an issue to review the model's analysis and the associated HTTP exchange.

{% hint style="warning" %}
AI-generated insights are leads for investigation, not confirmed vulnerabilities. Validate the evidence and reproduce suspected vulnerabilities before including them in a report.
{% endhint %}

AI Chat responses appear directly in the chat history rather than as Burp issues. See [Analyse HTTP traffic](/analysis-and-prompts/analyse-http-traffic) for the available workflows.


# Use AI Chat

Ask questions about selected HTTP traffic in the AI Chat editor.

## Before you start

[Activate your licence](/getting-started/activate-your-licence) and [test your provider](/model-setup/test-and-validate-model-provider-settings). Have a captured request available in a supported HTTP request editor, such as Proxy HTTP history or Repeater.

`AI Chat` does not require `Scan: On` or use the scanner's role, prompt template, or placeholders. It uses the provider, model, timeout, and request parameters from `Provider settings`.

## Ask a question

1. Select a request in Burp Suite.
2. Open the `AI Chat` tab in its message editor.
3. Type your question.
4. Select `Request`, `Response`, or both to include that traffic with your next message. A response can only be included when one is available.
5. Click `Send` or press `Ctrl+Enter`.

**Expected result:** The model's reply appears in the chat history. Ask another question to continue the conversation; chat replies do not create Burp issues.

## Conversation context

The chat retains up to 16 successful question-and-answer exchanges for model context. Each new request includes up to 15 previous exchanges plus your new message. Failed requests are not added to this context. Older exchanges remain visible in the editor but are no longer sent to the model. Restate important details when continuing a long conversation.

The current request and its available response are selected automatically when traffic is loaded into the editor. You can deselect either before sending. When you send a message, each included traffic toggle is deselected immediately, even if the model request later fails. Select it again to attach the current request or response to a later message.

{% hint style="warning" %}
Clearing a traffic toggle does not remove traffic already sent in earlier messages: that traffic can still be included in subsequent conversation context. Selecting another request in the same editor does not clear the conversation. Use `Clear chat` before starting a separate investigation.
{% endhint %}

`Clear chat` clears the displayed conversation and the context held by that editor; it does not delete data already received by your provider. Chat history is held in memory rather than saved as Burp issues or restored by the extension after reload.


# FAQ

Find answers about licensing, subscriptions, model-provider costs, data handling, and AI-generated insights.

This section answers common questions about BurpGPT Pro licensing, subscriptions, provider usage, local model privacy, and result accuracy.

For setup or provider errors, see [Troubleshooting](/help-and-faq/troubleshooting).


# Can BurpGPT Pro be used as a standalone application?

Understand why BurpGPT Pro requires Burp Suite Professional.

No. It is a Burp Suite Professional extension and cannot run as a standalone application.

To use it, you need Burp Suite Professional installed and an active Burp Suite Professional licence.


# Does the BurpGPT Pro licence include model-provider usage?

Understand model-provider costs and API access requirements.

No. Provider accounts, API access, quotas, and usage costs are separate from your BurpGPT Pro licence.

Review your chosen provider's API pricing:

* [OpenAI](https://developers.openai.com/api/docs/pricing)
* [Anthropic](https://www.anthropic.com/pricing)
* [Google AI Gemini](https://ai.google.dev/gemini-api/docs/pricing)
* [Mistral AI](https://mistral.ai/pricing/)

For self-hosted models, you are responsible for the model server and its infrastructure costs.


# Where is my analysis data sent?

Understand where prompts, chat messages, and HTTP traffic are sent for model processing.

Model requests are sent to the endpoint configured in `Provider settings`. They include your prompts, chat context, and any HTTP traffic selected for analysis.

A local or self-hosted endpoint can keep model processing on infrastructure you control, provided its runtime does not forward requests to a cloud service. For example, Ollama supports both local and cloud models.

An OpenAI-compatible endpoint does not have to be operated by OpenAI. Check the endpoint operator's policies and your runtime configuration to understand where processing occurs.

HTTP traffic is not automatically redacted. Review the data you include through [scanner placeholders](/analysis-and-prompts/use-placeholder-reference) or [AI Chat context](/analysis-and-prompts/use-ai-chat#conversation-context). Provider requests are also available in Burp's `Logger`.


# How can I cancel my subscription?

Manage or cancel your BurpGPT Pro subscription.

1. Open the [subscription portal](https://billing.stripe.com/p/login/3cs4gkff48YDf7y144), or use `Manage Subscription` in your purchase email.
2. Sign in with the email address used for your subscription.
3. Select the subscription and follow the cancellation steps.

The portal also provides access to your subscription and billing information.


# How do I purchase and manage licences as a reseller?

Purchase and manage BurpGPT Pro licences on behalf of clients.

Resellers can purchase multiple licences through [checkout](https://buy.stripe.com/dR6dSj1Hn8ni2I0fYY).

After payment, the checkout email address receives a welcome pack containing a JAR download link valid for 10 days, invoice details, and a subscription management link.

Choose the checkout email address according to who should manage the subscription:

* Use your own email address to receive the welcome pack, then forward the relevant information to your client.
* Use your client's email address for them to receive the welcome pack directly.

Subscriptions renew annually using the original payment method unless cancelled. See [Cancel your subscription](/help-and-faq/faq/how-can-i-cancel-my-subscription) for cancellation instructions.


# Can BurpGPT Pro produce false positive results?

Understand the limits of AI-generated insights.

Yes. Models can misinterpret traffic, suggest unsupported vulnerabilities, or miss genuine issues. Output quality depends on the model, prompt, and evidence provided.

Treat generated insights as leads for investigation, not confirmed findings. See [Review AI-generated insights](/analysis-and-prompts/view-gpt-generated-results) for how to interpret and validate the output.


# Why did licence activation fail?

Resolve common licence activation problems.

Select BurpGPT Pro under `Extensions` → `Installed` and check the `Errors` tab. If the message includes an HTTP status code, include it when contacting support. If no status code appears, check your licence key and network access using the checklist below.

Check the following:

* **Licence key:** Copy the complete key from your purchase email and confirm that the licence is still valid.
* **Network access:** Allow HTTPS access to `burpgpt.app` and `burpgpt.netlify.app` through your firewall or network controls.
* **Activation allowance:** Check the activation count displayed in the licence dialog. Contact support if you need help with your allowance.
* **System time:** Ensure your computer's date, time, and time zone are correct.
* **Installation:** Check the [requirements](/getting-started/installation#prerequisites). If the JAR is damaged, download a fresh copy.

If the problem persists, provide support with your extension version, Burp version, order ID, and error message. Do not post your licence key publicly.


# What is the licence activation allowance?

Check the activation allowance for a BurpGPT Pro licence.

A standard licence includes up to **three activations**. The licence dialog shows the used and allowed activations.

`Activate` consumes an activation each time it succeeds, even on a previously used computer. **Used activations cannot be recovered.** Use `Refresh` to check an existing saved licence without consuming another activation.

Check your remaining allowance before activating again. See [Activate your licence](/getting-started/activate-your-licence) for activation and refresh instructions.


# Troubleshooting

Resolve common installation, provider, scanning, and AI Chat problems.

Inspect provider requests and responses in Burp's `Logger` when diagnosing model connection problems.

Under `Extensions` → `Installed`, select BurpGPT Pro and check `Errors` for startup and operation failures. Check `Output` for messages prefixed with `Warning:` and follow any suggested action.

## The extension does not load

* Use Burp Suite Professional 2026.7 or later.
* If you launch Burp with an external Java runtime, use Java 21 or later.
* Check the extension error output. If the JAR is damaged, download a fresh copy.

See [Installation](/getting-started/installation).

## The extension loads, but features are not visible

Open `BurpGPT Pro` → `Licence` and check the displayed status. See [Activate your licence](/getting-started/activate-your-licence) or [Why did licence activation fail?](/help-and-faq/faq/what-are-the-possible-causes-for-an-unsuccessful-activation-of-my-burpgpt-pro).

## Provider settings reset after upgrading

Version 3.1 resets provider and scanner settings from earlier releases. Re-enter the provider configuration, run `Test request`, and review your scanner preferences. Saved licences and prompt libraries are retained.

## Settings cannot be saved

Provider and scanner settings are saved automatically as you edit them. If a save fails, the page displays an inline error and the extension records the failure in `Errors`. The failed edit has not been saved, even if it remains visible in the field. Check the error output before continuing.

## `Test request` fails

Inspect the provider response in `Logger`, then check:

* The provider matches the endpoint, and `Base URL` is correct.
* `API key` is present when required.
* `Model` is an exact identifier available to your account or model server.
* You pressed Enter after typing a custom model identifier; the dropdown's examples do not confirm availability.
* `Request parameters` contains valid JSON and [supported fields](/getting-started/supported-model-providers#request-parameters) with the correct types.
* The model supports the parameters you supplied. Try `{}` to remove optional parameters.
* Your provider has sufficient quota, credits, or local resources.
* `Read timeout` is long enough for the model to respond.

For HTTPS endpoints, certificate verification must succeed. If an HTTPS connection fails, check the certificate, hostname, and trust configuration.

See [Test your provider](/model-setup/test-and-validate-model-provider-settings).

## A local provider does not connect

Confirm that the model server is running and reachable from the computer running Burp. If it uses another host or port, update `Base URL`.

For Ollama, use `http://localhost:11434` for a standard local installation and confirm your model is available with `ollama ls`.

For OpenAI-compatible APIs, use the API base URL, typically ending in `/v1`, rather than the full `/chat/completions` URL.

## A test succeeds, but a scan or chat request fails

The actual prompt may be larger than the test request. Inspect the provider response for a context-limit error or timeout. Use narrower [placeholders](/analysis-and-prompts/use-placeholder-reference), reduce the included traffic, or increase the timeout as appropriate.

`max_tokens` limits generated output; it does not reduce the input prompt.

## Scans do not produce results

* Confirm that `Test request` succeeds.
* Review the role and prompt in `AI scanner`.
* For automatic analysis, enable `Scan: On` and start an active scan in Burp. The toggle does not scan Proxy history on its own.
* For targeted analysis, use `Extensions` → `BurpGPT Pro` → `Scan with AI (results in Target → Site map)`.
* Look for **GPT-generated insights** issues in `Target` → `Site map`.

See [Analyse HTTP traffic](/analysis-and-prompts/analyse-http-traffic).

## AI Chat does not include the expected traffic

Select `Request`, `Response`, or both before sending your message. A response is only available when one exists for the selected request.

Included traffic toggles are deselected when you send a message, even if the model request later fails. Select them again to attach the current traffic to another message. Previously sent traffic can still be included in conversation history: unticking Request or Response does not remove it. Selecting another request in the same editor does not clear the conversation either; use `Clear chat` before a separate investigation.

Each model request includes up to 15 previous completed exchanges plus your new message. Older exchanges remain visible but are no longer sent. See [conversation context](/analysis-and-prompts/use-ai-chat#conversation-context).

## A prompt import fails or replaces an entry

Import a JSON array in the [prompt library format](/analysis-and-prompts/use-the-prompt-library#import-prompts). Each entry needs non-blank `author`, `category`, and `text` fields.

Imports update existing entries with the same ID. Different IDs remain separate, even if the prompt text matches. Export a backup before importing or resetting the library.


# Changelog

Review features, fixes, and compatibility changes across BurpGPT Pro releases.

## 3.1 (14/10/2026)

{% hint style="info" %}
BurpGPT Pro 3.1 expands scanner prompt placeholders and improves navigation, AI Chat, provider configuration, and the prompt library.
{% endhint %}

### Added

* Added a search field to filter settings pages in the sidebar.
* Expanded scanner prompt placeholders to include target details, request parameters, response status, cookies, annotations, and timing information. The `Placeholder reference` page lists the available placeholders and their descriptions.
* Added inline validation of supported parameter names and value types in the `Request parameters` editor, with clearer error messages and highlighting.
* Added inline feedback when provider or scanner settings cannot be saved.

### Changed

* Refreshed settings pages, page headers, and AI Chat layouts for a more consistent experience with Burp's light and dark themes.
* Updated the licence dialog with clearer status descriptions, aligned details, and more consistent activation controls.
* Improved text contrast in the `About` window in both themes.
* Improved error messages and warnings to make activation, configuration, and connection problems easier to troubleshoot.
* Updated the bundled example prompts for OWASP Top 10:2025 and API security reviews, with a stronger focus on evidence, confidence, and follow-up tests.
* AI Chat now sends only recent conversation exchanges as context. Older exchanges remain visible in the conversation.
* Kept the interface responsive during prompt library imports and exports.
* Simplified provider timeout configuration to a single response timeout in seconds.
* Refreshed the model example list while retaining support for custom model names.

### Fixed

* Fixed table context menus failing when identifier columns, such as `#` or `Placeholder`, are hidden.
* Fixed table search counts not updating after changes to the displayed data.
* Improved compatibility with provider endpoints that use URL query parameters or custom ports.
* Fixed encoding issues in provider requests and responses, including non-ASCII text.
* Fixed display of AI-generated findings containing HTML or XML text.
* Failed AI Chat requests no longer leave an unanswered message in the context sent with later requests.
* Improved cleanup when unloading the extension.

### Compatibility

* Raised the minimum supported Burp Suite Professional version to `2026.7`.
* Provider and scanner settings from earlier releases reset to defaults on upgrade. Re-enter your provider configuration and check your scanner preferences before use.
* Existing prompt libraries are retained. To load the new example prompts, export any custom prompts before resetting the library to defaults.
* HTTPS provider requests now enforce server certificate verification. Custom HTTPS endpoints must pass certificate verification to connect.

## 3.0 (12/05/2026)

{% hint style="info" %}
BurpGPT Pro 3.0 introduces a redesigned interface, unified provider configuration, local/self-hosted provider support through standard APIs, and an interactive `AI Chat` workflow.
{% endhint %}

### Added

* Added the `AI Chat` request editor tab for follow-up questions about selected HTTP traffic.
* Added `Request` and `Response` context toggles in `AI Chat`.
* Added `OpenAI-compatible API` as a provider option for local, self-hosted, and compatible third-party endpoints.
* Added a dedicated licence dialog showing activation status, validity dates, activation count, and licensed email.
* Added `Test request` to validate the active provider configuration before scanning or chatting.

### Changed

* Redesigned the user interface to provide a more modern, consistent, and streamlined experience.
* Unified model configuration under the `Provider settings` tab.
* Moved scan-specific role and prompt configuration to the `AI scanner` tab.
* Active scan registration is now controlled by the `Scan: Off` / `Scan: On` toggle in `AI scanner`.
* Replaced the previous Python/Hugging Face local server workflow with Ollama and OpenAI-compatible provider integrations.

### Compatibility

* Raised the minimum supported Burp Suite Professional version to `2026.4`.

### Removed

* Removed unnecessary bundled dependencies.

## 2.0 (07/08/2025)

{% hint style="info" %}
BurpGPT Pro 2.0 expanded provider support and introduced a refreshed configuration workflow.
{% endhint %}

### Added

* Added out-of-the-box support for Anthropic, Google AI Gemini, Mistral AI, OpenAI, and local/custom providers.
* Added adjustable timeout controls for provider requests.
* Added fine-grained `Request parameters` for provider-specific model options.
* Added in-app tooltips and contextual usage hints.

### Changed

* Streamlined the user interface for provider setup and scanning.
* Centralised configuration in `Provider settings`.
* Simplified scan control with the `Scan: Off` / `Scan: On` toggle.
* Unified contextual scan actions so requests and responses use the current provider configuration.

## 1.1 (13/02/2025)

### Added

* Added a `Report Bug` menu item to the BurpGPT Pro menu.

### Changed

* Replaced the `About` view with an `About` menu item that opens a compact version dialog.
* Standardised layout margins across the extension.
* Improved prompt library interactions, including disabled states for unavailable actions and a larger `Add prompt` dialog.

### Fixed

* Improved error handling and general stability.

## 1.0.2 (26/01/2025)

### Added

* Added documentation and release-note links to the BurpGPT Pro menu.

### Changed

* Updated the required Python binary version for the legacy local LLM workflow to `3.12.6`.

### Fixed

* Fixed duplicate requests when using `Send to <LLM_PROVIDER>`.
* Included general bug fixes and performance improvements.

## 1.0.1 (19/09/2024)

### Changed

* Removed a confusing Swing component warning from the user-facing output.
* Added a Burp Suite version check with an upgrade prompt when required.

### Fixed

* Fixed missing query strings in requests sent to `LLM_PROVIDER`.
* Included general bug fixes and performance improvements.

## 1.0 (20/08/2024)

### Added

* Added direct request handling through Burp Suite for selected LLM providers.
* Added Burp `Logger` visibility for provider requests and responses.
* Added Burp `Dashboard` tasks for context-menu provider actions.
* Added editable `model` and `role` fields.
* Added copy and cut support for `API endpoint` and `API key` fields.
* Added prompt text wrapping.
* Added `Roles` and `Max New Tokens` controls for the legacy local LLM workflow.
* Added prompt library context-menu actions for copying selected rows as JSON and copying cell values.
* Added export support for legacy local server logs.

### Changed

* Sent Azure/OpenAI API requests over `HTTP/2`.
* Improved extension performance and stability.
* Improved legacy local LLM request handling and processing speed.
* Displayed legacy local server output in Burp Suite's `Raw Editor`.
* Refreshed navigation tabs, icons, prompt dialogs, status colours, and `About` view layout.
* Standardised button labels.

### Fixed

* Improved logging and exception handling.
* Included general bug fixes and performance improvements.

## 0.4.8 (30/05/2024)

### Added

* Added support for the `gpt4-turbo` and `gpt4-o` models.
* Added a documentation link to the `About` view.

### Fixed

* Included general bug fixes and performance improvements.

## 0.4.7 (01/04/2024)

### Added

* Added an `Anonymise report` option to hide the `API endpoint` and `API key` in generated GPT insight issues.
* Added a clear validation warning to generated issue background text.

### Changed

* Increased the default `Request timeout (seconds)` value from `10` to `30`.
* Allowed `Max prompt length` set to `0` to disable prompt truncation.
* Reorganised the `Azure/OpenAI API` and `Local LLM` settings layout.
* Standardised wording for Burp Suite context-menu actions.

### Fixed

* Fixed an issue with the `Request timeout (seconds)` slider introduced in `0.4.6`.
* Included general bug fixes and performance improvements.

## 0.4.6 (04/03/2024)

### Added

* Added a `Request timeout (seconds)` slider for provider calls.
* Added tooltips to `Browse` buttons in the legacy local model settings.

### Changed

* Improved table space in the `Prompt` and `Placeholder` tabs.
* Standardised `Prompt library` context-menu wording.

### Fixed

* Fixed `Prompt library` context-menu actions using the `Author` column instead of the selected prompt text.
* Included general bug fixes and performance improvements.

## 0.4.5 (22/02/2024)

### Added

* Added `#`, `Author`, and `Created` columns to the prompt library.
* Added a show/hide toggle for `API endpoint` and `API key` fields.
* Added a tooltip for the settings icon.

### Changed

* Sorted the prompt table by `Category` by default.
* Updated the prompt library layout.
* Aligned table behaviour with current Burp Suite table controls for column visibility and sorting.

### Fixed

* Fixed issues related to the extension persistence store.
* Included general bug fixes and performance improvements.

## 0.4.4 (29/01/2024)

### Added

* Added visual feedback for legacy local model downloads and related provider activity.
* Added a `Python path` field for environments with restricted system `PATH` access.

### Changed

* Updated the tab name from `OpenAI API` to `Azure/OpenAI API`.
* Simplified the call-to-action colour scheme.
* Enabled auto-scrolling in the legacy server debug view.
* Reworked the legacy local model server view.

### Fixed

* Fixed Azure OpenAI Services integration issues.
* Included general bug fixes and performance improvements.

## 0.4.3 (16/01/2024)

### Changed

* Updated OpenAI defaults from the completions API to the chat completions API.
* Removed deprecated OpenAI models from the model list.
* Improved settings persistence across versions.
* Reduced bundle size by removing unused legacy local model dependencies.

### Fixed

* Included general bug fixes and performance improvements.

## 0.4.2 (07/01/2024)

### Added

* Added arbitrary endpoint support for the `API endpoint` field.
* Added prompt library context-menu actions for sending prompts to provider views.
* Added logging updates for newer Montoya API behaviour.

### Changed

* Added `Settings` menus with `Restore defaults` to provider views.
* Switched to Font Awesome icons.
* Improved icon hover states.
* Removed the `Docking` button after Burp Suite added native tab docking support.

### Fixed

* Included general bug fixes and performance improvements.

## 0.4.1 (05/06/2023)

### Fixed

* Included general bug fixes and performance improvements.

## 0.4 (02/06/2023)

### Added

* Added settings persistence for `OpenAI API` and `Local LLM` views.
* Added a `Reset` button for restoring default field values.

### Changed

* Improved cross-platform compatibility, particularly on macOS.
* Unified the extension user interface.

### Fixed

* Included general bug fixes and performance improvements.

## 0.3 (25/05/2023)

### Added

* Added built-in example prompts to the `Prompt library`.
* Added compatibility for `text-davinci-002`, `text-davinci-003`, `text-ada-001`, `text-babbage-001`, and `text-curie-001`.
* Added tooltips for key fields.

### Changed

* Improved cross-platform compatibility, particularly on macOS.
* Improved legacy local server start and stop behaviour.
* Improved extension unload handling.
* Refined settings persistence.
* Removed the `Apply` button and applied setting changes automatically.
* Unified the extension user interface.

### Fixed

* Fixed a bug that prevented licence activation issues from being displayed.
* Included general bug fixes and performance improvements.

## 0.2.2 (22/05/2023)

### Changed

* Improved logging for troubleshooting.

### Fixed

* Fixed a UI bug where the `Parameter #` field remained enabled when text was entered in the `LLM directory` field.
* Included general bug fixes and performance improvements.

## 0.2.1 (19/05/2023)

### Changed

* Reduced the jar size by removing bundled Python dependencies.

### Fixed

* Fixed Python compatibility issues affecting the legacy local LLM workflow.

## 0.2 (16/05/2023)

### Added

* Added a `Dock` button for switching between floating and suite tabs.

### Changed

* Improved legacy local model processing performance.
* Improved application stability and reliability through broader exception handling.

### Fixed

* Fixed a visual issue that caused the prompt text field to collapse with larger font sizes.

## 0.1.1 (11/05/2023)

### Fixed

* Included bug fixes and performance improvements.

## 0.1 (07/05/2023)

### Added

* Initial BurpGPT Pro release.


# Roadmap

Explore planned improvements for BurpGPT Pro.

The following improvement is planned. Scope and release timing may change.

* Support multi-message scanner prompts for compatible models, replacing the single role and prompt with a messages editor.

For features already delivered, see the [changelog](/help-and-faq/changelog).