Anthropic

Your channels

Questions from your channelsYour API key

answerLoops

1. Find the answer
2. Draft the answer
3. Review confidence

What you control

• Billed to you
• Included usage for search
• Model choice

Answering is billed to your Anthropic account

Anthropic's Claude models generate the answers answerLoops drafts. Claude handles chat only, because Anthropic doesn't offer embeddings.

OpenAI is the only provider that can handle knowledge-base processing (embeddings) today. Google Gemini and Mistral are coming soon. On a hosted plan, knowledge-base processing runs on your plan's included AI usage until you add an OpenAI key under Embeddings, which removes that limit. Self-hosted installs need an OpenAI key (or a custom embedding endpoint).

Available on every plan. Usage bills to your Anthropic account.

1. Get an API keyCopy Anchor Link

In the Anthropic Console, create a key. Make sure the workspace has credit or billing configured.

2. Configure in answerLoopsCopy Anchor Link

1. Settings → AI Model → Edit (owner or admin).
2. Chat provider: Anthropic.
3. Model ID: e.g. claude-sonnet-4-6, claude-haiku-4-5-20251001 — the field suggests current options; see the Claude models list for exact names.
4. API key: paste your Anthropic key.
5. Embeddings: leave the provider on OpenAI. On a hosted plan the OpenAI API key field is optional: leave it blank to use included AI usage for knowledge-base processing, or add a key to remove the limit. Self-hosted installs must enter one, or knowledge-base search and KB imports fail after you save. answerLoops tells you if it's missing.
6. Click Test connection. It checks the Claude key, and it checks the OpenAI embedding key separately if you entered one (otherwise it tells you knowledge-base processing will use included AI usage). Then Save.

ModelsCopy Anchor Link

RelatedCopy Anchor Link

• AI Model settings — how embeddings and included usage work, and how provider switching is handled
• OpenAI integration — for an OpenAI embedding key