The Claude API integration connects ThunderAI to Anthropic's Claude AI models.
Claude is known for producing careful, well-structured responses and handling long documents well — a great fit for reading and composing detailed emails.

Prerequisites

• An Anthropic account with API access
• A valid Claude API key
• Thunderbird with ThunderAI installed

Getting an API key

1. Go to console.anthropic.com/settings/keys
2. Click Create Key
3. Give it a name and copy the key immediately, it will not be shown again

Setup

The quickest way is the Setup Wizard: open it from the ThunderAI welcome page, the toolbar popup or the settings page, choose Claude API, paste your API key, choose a model and test the connection. The wizard then lets you turn on the AI features you want.
To set it up by hand, follow the steps below.

1. Open the ThunderAI settings

In Thunderbird, go to Tools → Add-ons and Themes → ThunderAI → Preferences.

2. Select the Claude API integration

In the Connection Settings panel, choose Claude API in the Connection Type dropdown.

3. Enter your API key

Paste your API key in the Claude API Key field. The key is stored locally in Thunderbird and never sent anywhere other than Anthropic's servers.

4. Choose a model

Click Update list next to Claude Models. The first time, Thunderbird asks for permission to access anthropic.com: accept it, or ThunderAI cannot reach the Claude API. Then select the model you want to use from the list.

This is an optional permission, used only to communicate with Anthropic's API servers. ThunderAI does not collect any data.

5. Test the connection

Settings are saved as soon as you change them: there is no Save button.
Click Test now in the bar below the connection settings. When everything is fine, it shows "Connected — Claude API reachable". Then open any email, click the ThunderAI toolbar button and run a prompt.

Advanced options

Click Advanced options in the Connection Settings panel to show the settings below. They adapt to the selected model: a setting the model does not accept is disabled, with a note that explains why, and is not sent. The saved value is kept, in case you switch back to another model.

• System Prompt: instructions and context sent to the model with every prompt.
• Max Tokens: the maximum length of the answer.
• Effort: how much reasoning the model spends on a request. Higher levels give better answers on complex tasks, but cost more tokens and take longer. Leave it on Default to let the API decide. Older Claude models do not support it.
• Extended thinking budget (tokens): for the older models, the maximum number of tokens the model can spend thinking. 0 turns extended thinking off. It must be at least 1024 and lower than Max Tokens: otherwise the settings show a warning and the value is not sent.
• Temperature (0.0–1.0), Top P and Top K: how random or focused the answer is. The newer Claude models do not accept them: use Effort instead.
• Stop sequences: text that makes the model stop writing, one per line. Accepted by every Claude model.
• Claude API Version: the version of the Anthropic API. Do not change it unless you know what you are doing.

You can also set these options on a single prompt, in the custom prompts page, and on each AI feature (Add Tags, Spam Filter, Summarize, Translate, Calendar Event, Task), with the Advanced options button of its specific connection.

Tips

• Claude models handle large amounts of text well thanks to their extended context window, useful when processing long email threads.
• Claude tends to be thorough in its responses. If you prefer shorter outputs, add instructions like "Be concise" directly in your prompts, in a custom prompt, or in the System Prompt.
• New Claude models work as soon as they appear in the list. If a model rejects one of the options, ThunderAI automatically repeats the request once without it.
• If Anthropic's rate limit is exceeded while ThunderAI processes several emails (Add Tags, Spam Filter, Summarize, Translate), the processing stops by itself and tells you how many messages were processed.
• Monitor your API usage and costs at console.anthropic.com.

Troubleshooting

"Authentication failed — check your API key" or "Invalid API key" error

Check that the key was copied correctly. Regenerate a new key from the Anthropic console if needed.

The popup asks for a permission instead of showing the prompts

The anthropic.com permission has not been granted yet, and without it ThunderAI cannot reach the Claude API. Click the message in the popup: the ThunderAI welcome page opens. Click the same message there and accept Thunderbird's request. You can also grant it from step 4.

"Credit balance too low" error

Add credits to your Anthropic account at console.anthropic.com/settings/billing.

No models appear in the list

If you see "You have denied the optional permission needed to fetch models for this integration", click Update list again and accept Thunderbird's permission request. Otherwise make sure your API key is valid.