> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.pensar.dev/apex/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.pensar.dev/apex/_mcp/server.

# /providers

> Manage AI providers and configure API keys

## Overview

The `/providers` command opens the provider management interface where you can connect and configure AI providers for use with Apex. This is where you set up your API keys to enable AI-powered penetration testing.

## Usage

```bash
/providers
```

## Supported Providers

Apex supports the following AI providers:

#### Anthropic

**Recommended** - Claude Pro/Max or API key. Best performance for
penetration testing tasks.

#### OpenAI

GPT 5.5, GPT-4, and other OpenAI models.

#### Google

Gemini models via Google's Generative AI API.

#### OpenRouter

Access multiple AI models through one API. Great for flexibility and model
comparison.

#### AWS Bedrock

Amazon Bedrock AI models for enterprise deployments.

#### Inference.net

DeepSeek V4.1 Flash 1017 Cyber. Requires approved model access for your
team.

#### Hoonify

Open models served by Hoonify. Available models are discovered using your
API key.

#### Pensar Console

Managed inference — connect via `/login` instead, no API key needed.

> **Success**
>
> **Anthropic is recommended** for optimal penetration testing performance.
> Claude models provide superior reasoning capabilities for security testing.

## How It Works

#### Open Provider Selection

Run `/providers` to open the provider selection interface

#### Choose Provider

Use `↑/↓` arrows to navigate and `[Enter]` to select a provider

#### Enter API Key

Input your API key for the selected provider. Apex verifies your key against the provider's API before saving — if the key is invalid, you'll see an inline error and can try again.

> **Info**
>
> Selecting **Pensar Console** from the provider list routes you to the `/login` device-flow login instead of the API key input screen.

#### Select Model

After configuring, you'll be redirected to `/models` to select a model

## Provider Setup

For Inference.net, create an API key at [inference.net](https://inference.net),
select **Inference.net** in `/providers`, then select **DeepSeek V4.1 Flash 1017
Cyber** in `/models`. You can also set `INFERENCE_API_KEY`. Your team must have
[approved access](https://inference.net/model-access/deepseek-v4.1-flash-1017-cyber)
to this model; a valid key alone does not grant access.

For Hoonify, create a subscription key at [app.hoonify.ai](https://app.hoonify.ai),
select **Hoonify** in `/providers`, and choose a discovered model in `/models`.
You can also launch Apex with `HOONIFY_API_KEY` set. Apex uses the exact model IDs
returned by Hoonify's catalog and any reported context windows. When context
metadata is absent, GLM-5.2 uses its deployed 500,000-token context budget;
other models without known limits use a 32,768-token context budget.
Set `HOONIFY_CONTEXT_WINDOWS` to a JSON object mapping exact model IDs to
context windows to override a limit. Responses are capped at 4,096 tokens
(lower for small context windows).

#### Anthropic

**Best for**: All penetration testing tasks

### Get Your API Key

1. Visit [console.anthropic.com](https://console.anthropic.com/)
2. Sign up or log in to your account
3. Navigate to API Keys section
4. Create a new API key

### Configure in Apex

1. Run `/providers`
2. Select "Anthropic"
3. Paste your API key
4. Press Enter to save

> **Info**
>
> Claude Pro/Max subscribers can use their subscription. API keys provide more flexibility for heavy usage.

#### OpenAI

**Best for**: Users already invested in the OpenAI ecosystem

Apex uses GPT 5.5 as the default OpenAI model when OpenAI is your highest-priority configured provider.

### Get Your API Key

1. Visit [platform.openai.com](https://platform.openai.com/)
2. Navigate to API Keys
3. Create a new secret key

### Configure in Apex

1. Run `/providers`
2. Select "OpenAI"
3. Paste your API key
4. Press Enter to save

#### Google

**Best for**: Users wanting access to Gemini models

### Get Your API Key

1. Visit [aistudio.google.com](https://aistudio.google.com/)
2. Sign in with your Google account
3. Generate an API key

### Configure in Apex

1. Run `/providers`
2. Select "Google"
3. Paste your API key
4. Press Enter to save

#### OpenRouter

**Best for**: Access to multiple models through a single API

### Get Your API Key

1. Visit [openrouter.ai](https://openrouter.ai/)
2. Create an account
3. Navigate to Keys section
4. Generate a new API key

### Configure in Apex

1. Run `/providers`
2. Select "OpenRouter"
3. Paste your API key
4. Press Enter to save

> **Info**
>
> OpenRouter provides access to models from multiple providers including
> Anthropic, OpenAI, Google, Meta, and more through a unified API.

#### AWS Bedrock

**Best for**: Enterprise deployments with existing AWS infrastructure

### Prerequisites

* AWS account with Bedrock access
* IAM permissions for Bedrock models
* Model access enabled in your region

### Get Your Credentials

1. Log in to AWS Console
2. Navigate to IAM
3. Create or use existing access keys
4. Ensure Bedrock permissions are attached

### Configure in Apex

1. Run `/providers`
2. Select "AWS Bedrock"
3. Enter your AWS credentials
4. Press Enter to save

> **Warning**
>
> Ensure your IAM role has permissions to invoke Bedrock models and that model access is enabled in your AWS region.

#### Pensar Console

**Best for**: Getting started quickly without managing API keys

Pensar Console provides managed inference so you don't need to bring your own API key.

### Connect

1. Run `/login` in Apex (not `/providers`)
2. Follow the authentication flow to link your Pensar Console account
3. Your models will appear automatically in `/models`

> **Info**
>
> Visit [console.pensar.dev](https://console.pensar.dev) to create an account and manage credits.

## Keyboard Navigation

| Key       | Action                     |
| --------- | -------------------------- |
| `[↑/↓]`   | Navigate between providers |
| `[Enter]` | Select provider            |
| `[ESC]`   | Close and return home      |

## Provider Status

In the provider selection screen, configured providers display a green checkmark (✓) indicating they're ready to use.

## After Configuration

Once you've configured a provider:

1. You'll be automatically redirected to the `/models` command
2. Select a model from your configured provider
3. Start testing with `/pentest`

## Quick Access

You can also access providers from the models screen:

* Press `Ctrl+P` while in `/models` to open provider management

## Security Best Practices

> **Warning**
>
> **API Key Security**: - Never share your API keys - Rotate keys periodically -
> Use separate keys for different environments - Monitor usage for unexpected
> activity

## Troubleshooting

#### API key not working

**Issue**: Provider shows configured but models won't load

**Solutions**:

1. Apex verifies keys on entry — if you see a verification error, double-check the key
2. Verify the API key is correct (no extra spaces)
3. Check that your account has credits/access
4. Ensure the key has appropriate permissions
5. Try regenerating the key

#### Provider not showing

**Issue**: Expected provider not in the list

**Solutions**:

1. Update Apex to the latest version (`pensar upgrade`)
2. Restart Apex
3. Check if provider requires additional setup

#### AWS Bedrock errors

**Issue**: Cannot connect to AWS Bedrock

**Solutions**:

1. Verify AWS credentials are correct
2. Check IAM permissions include Bedrock access
3. Ensure model access is enabled in your region
4. Verify your account has Bedrock quota

## Related Commands

#### [/models](/apex/tui-slash-commands/models)

Select AI model after configuring provider

#### [/pentest](/apex/tui-slash-commands/pentest)

Start a penetration test

#### [/help](/apex/tui-slash-commands/help)

View all available commands