Set up AI
AI3 min read

How to enable BYOK AI and switch providers

NexoPad AI works in BYOK mode: you choose the provider, save your key, and control the model.

On this page · 3 sections
  1. 1Initial setup
  2. 2Providers and models
  3. 3Privacy and availability

The extension does not lock you into a single provider. You can store several keys, activate one or another depending on the case, and choose a different model for each service.

The approach remains BYOK: the key comes from your own account and is used to call the chosen provider, not to send it to a NexoPad backend.

1How to activate AI

1

Open AI settings from the side panel or popup

The current version lets you manage multiple providers from one place and activate the one you want to use at that moment.

2

Save one or more API keys

You can keep several keys at once and switch between them without redoing the entire setup each time. The interface tries to validate the key before it becomes the active configuration.

3

Activate the provider and choose the model

You can use the suggested default model or type a custom name if your account supports another compatible model.

4

Adjust persona, options, and target language if needed

Besides the provider itself, you can now also define a persona or system prompt and other settings tied to the AI experience.

5

Go back to the panel and test a real text action

That confirms in a real scenario that your provider, key, and model are working as expected.

Choose a provider and model, then paste your key.
Once the key is saved, the panel shows the active provider.
The gear opens the settings: your AI, its model, "Change AI" and the key icon to change your API key.
"Change AI" lists your connected AIs and the ones you can add, free ones first.
2

Providers and default models detected in the extension

ProviderDefault modelUseful note
Groq
Default model
llama-3.3-70b-versatile
Useful note
Often a fast option to start with your own key.
Mistral AI
Default model
mistral-small-latest
Useful note
Additional provider supported directly by the extension.
Cohere
Default model
command-r-plus-08-2024
Useful note
Available as a native option in the provider selector.
OpenRouter
Default model
openai/gpt-oss-120b:free
Useful note
Presented by NexoPad as a useful path for accessible or free catalog models.
OpenAI
Default model
gpt-4o-mini
Useful note
You can switch to another compatible model if your account supports it.
Anthropic
Default model
claude-haiku-4-5-20251001
Useful note
Designed for fast answers with contained cost.
Google Gemini
Default model
gemini-2.0-flash
Useful note
A lighter option for short tasks.
DeepSeek
Default model
deepseek-chat
Useful note
Can also switch to other compatible models from the provider.
xAI (Grok)
Default model
grok-3-mini
Useful note
Supports custom model names if your account allows it.
Together AI
Default model
meta-llama/Llama-3.3-70B-Instruct-Turbo
Useful note
Another provider directly supported in the current selector.

3Privacy, errors, and availability

The extension is built with a BYOK approach: your API key is stored to call the chosen provider directly, not to send it to NexoPad-owned servers.

If you see a provider unavailable error, check four things first: whether the key is still active, whether you have quota or credit when applicable, whether the model exists for your account, and whether the provider is available in your region.

The availability of free or low-cost models can change over time depending on the provider policy. The important point is that NexoPad exposes the selector, but the real catalog depends on your account and on the external service.

Important

If you work with sensitive information, prioritize a provider whose policy and region have already been approved by your team. Fast switching between engines is useful, but it does not replace compliance review.