Skip to main content

​
Provider Keys Management

The Provider Keys Management system allows you to securely store and manage API keys for multiple AI providers. This enables you to use different models and services across your experts and assistants.

​
Overview

Provider keys are used to authenticate with various AI services including:
  • LLM Providers: OpenAI, Anthropic, Google, Mistral, DeepSeek, and more
  • Voice Providers: ElevenLabs, OpenAI TTS, Google TTS, Azure Speech
  • Image Providers: Stability AI, Midjourney, OpenAI DALL-E

​
Accessing Provider Keys

Navigate to Profile → Provider Keys or Settings → API Keys to manage your keys.

​
Adding a Provider Key

1

Select Provider

Click Add New Key and choose your provider from the list. You can filter by category:
  • All: Show all providers
  • LLM: Language model providers
  • Voice: Text-to-speech providers
  • Image: Image generation providers
2

Enter API Key

Paste your API key from the provider’s dashboard. The key will be encrypted before storage.
3

Configure Settings

  • Nickname: Give your key a memorable name (optional)
  • Primary: Set as the default key for this provider
  • Fallback: Use this key if the primary fails
4

Save

Click Save to securely store your key. It will be validated with the provider.

​
Supported Providers

​
LLM Providers

OpenAI

GPT-4, GPT-4 Turbo, GPT-3.5

Anthropic

Claude 3 Opus, Sonnet, Haiku

Google

Gemini Pro, Gemini Ultra

Mistral AI

Mistral Large, Medium, Small

DeepSeek

DeepSeek Chat, Coder

Cohere

Command, Command-R

Groq

Ultra-fast inference

Azure OpenAI

Azure-hosted models

Ollama

Self-hosted local models

​
Voice Providers

ElevenLabs

High-quality voice synthesis

OpenAI TTS

Natural-sounding voices

Google TTS

Multi-language support

Azure Speech

Neural voices

​
Image Providers

Stability AI

Stable Diffusion models

OpenAI DALL-E

DALL-E 3 image generation

Midjourney

Artistic image creation

​
Key Management Features

​
Primary Keys

Set a key as Primary to make it the default for that provider. When you select a model from that provider, it will automatically use the primary key.

​
Fallback Keys

Set a key as Fallback to provide redundancy. If the primary key fails (rate limit, quota exceeded, etc.), the system will automatically try the fallback key.

​
Key Validation

When you add a key, B-Bot Hub validates it with the provider to ensure it’s working correctly. You’ll see a validation status indicator.

​
Nickname System

Give your keys memorable nicknames like:
  • “Production OpenAI”
  • “Development Key”
  • “High-Limit Account”
  • “Personal ElevenLabs”
This makes it easy to identify which key to use for different purposes.

​
Using Provider Keys

​
In Expert Creation

When creating an expert and selecting a model, you can choose which provider key to use:
  1. Use Expert’s Main Key: The primary key for that provider
  2. Select Specific Key: Choose from your available keys for that provider

​
In Modalities

For voice input/output, you can select different keys for TTS than your main model key: 
Main Model: GPT-4 (using "Production OpenAI")
Voice Output: ElevenLabs (using "Personal ElevenLabs")

​
In Assistants

Each assistant can be configured with its own provider key selection for maximum flexibility.

​
Security Best Practices

API keys are sensitive credentials. Follow these security practices:
All API keys are encrypted before storage using industry-standard encryption. Keys are only decrypted when making API calls.
Regularly rotate your API keys, especially for production use. Update keys in B-Bot Hub when you rotate them with providers.
Use separate keys for development and production environments. This prevents accidental quota usage.
Regularly check your provider dashboards for unusual API usage that might indicate unauthorized access.
When possible, create provider keys with minimal required permissions.

​
Managing Multiple Keys

You can have multiple keys for the same provider. This is useful for:
  • Load Balancing: Distribute requests across multiple accounts
  • Rate Limit Management: Switch to a different key when limits are reached
  • Team Management: Different keys for different team members or projects
  • Cost Tracking: Separate keys for different clients or departments

​
Troubleshooting

Possible causes:
  • Invalid API key format
  • Key has been revoked
  • Provider service is down
  • Network connectivity issues
Solution: Double-check the key in your provider dashboard and try again.
Solution: Add a fallback key or wait for your rate limit to reset. Consider upgrading your provider plan.
Possible causes:
  • Key is for a different provider than the selected model
  • Key validation hasn’t completed
Solution: Ensure the key’s provider matches your model selection.

​
Getting API Keys from Providers

​
OpenAI

  1. Go to platform.openai.com
  2. Navigate to API Keys
  3. Click Create new secret key
  4. Copy the key immediately (you won’t see it again)

​
Anthropic

  1. Go to console.anthropic.com
  2. Navigate to API Keys
  3. Click Create Key
  4. Copy and save the key

​
ElevenLabs

  1. Go to elevenlabs.io
  2. Navigate to Profile → API Keys
  3. Generate a new key
  4. Copy the key
Each provider has its own process for generating API keys. Refer to their documentation for specific instructions.

​
Next Steps

Create Your Expert

Use your provider keys to create powerful AI experts

Configure Modalities

Set up voice input and output with your keys