Introduction

In this guide we'll walk through the process of linking Cerb to Anthropic. You'll be able to use Anthropic's full API in Cerb automations as a LLM provider.

Get an Anthropic API Key.

Select API keys in the left navigation. It's a top-level item, second under Dashboard – there's no Settings step to go through first.
Click the Create key button.
A modal appears offering identity federation instead, headed "With identity federation, you don't need an API key". Its primary button sets that up; the one you want is the secondary, Continue with an API key.
In the Create API key dialog, give the key a Name (eg. cerb) and choose when it Expires. Linked account and Scope are there too. Click Create key.
The key is shown once, under Save your API key – "Keep a record of the key below. You won't be able to view it again." Click Copy key and keep it somewhere safe for the next step, then Done.

Create the Anthropic service in Cerb

Navigate to Search » Connected Services.
Click the (+) icon in the top right of the list.
Select Anthropic.
Paste the key you copied earlier in the API Key field.
Click the Create button.

Create an agent model

An agent model record holds one model's configuration – its provider, endpoint and credentials – so automations reference it by name instead of repeating a provider block.

The fields below are in the order the form presents them. API endpoint URL comes before Model because it feeds both Refresh and Test.

Navigate to Search » Agent Models.
Click the (+) icon in the top right of the list.
Set Provider to Anthropic.
Leave API endpoint URL blank. Its placeholder reads (auto), and blank uses https://api.anthropic.com. Set it only for a proxy or a self-hosted endpoint.
Set Authentication to the connected account you created above. The field isn't marked required, because a local provider needs none – but a hosted one will fail to authenticate without it.
Click the refresh button beside Model to load the provider's live model list, and pick one.
Give the record a short Name – this is what automations will use. Colons aren't allowed, since the name is referenced as cerb:agent_model:<name>.
Click Test to verify the connection, then Create.

Refresh is on demand, and it never happens quietly. Until a refresh succeeds, the suggestions under Model are a hardcoded list rather than your account's – there's deliberately no silent fallback, so a failed fetch looks like one instead of looking like nothing happened. Refreshing requires an administrator; a non-admin gets a permission error rather than an empty list. The field is free text throughout, so a model id works the day it ships even if the list hasn't caught up.

Give the refresh a moment to land before you open the Model menu. Opening it too early shows the shipped suggestions rather than your account's models, and the menu keeps showing them until you close and reopen it. Those are real model ids, so there's nothing on screen to tell you apart from a list that loaded – which is the other reason to check the context window on whatever you picked.

Picking a model from a refreshed list fills exactly three things: the Name, Vision and Context window – and the last two only for ids beginning claude-, which is what Cerb's table is gated on. Nothing else on the form changes – Thinking and the four Ratings are yours to set, and Cerb emits no per-model description for this provider, so the hint line under Model stays empty. Both values come from a table built into Cerb rather than from Anthropic, so check both and set either yourself if it's wrong for your model. The Name is rewritten to a sanitized version of the model id every time, including on a record you already named, so give the record its name after you pick, not before.

Vision is asserted for the whole claude- family, not looked up per model. The note beside it in Cerb's source reads "Every current Claude model is multimodal; only the context window varies by tier" – accurate when it was written, and it stops being accurate the day Anthropic ships a text-only model, which would then be marked as accepting images. A wrong Vision hands workers an image attachment the model rejects.

The window does vary by tier, with a blanket fallback: any claude- id Cerb doesn't recognize is given 200000. So a model released after your version of Cerb still gets a context window – a plausible one rather than a correct one, with nothing saying which you got. Compaction ratios are fractions of it.

Only a refreshed list carries that metadata. Before you click refresh, the suggestions under Model are a shipped list of hints, and picking one of those fills in the Name and nothing else – no context window, no capabilities. These values arrive with the model list, not with the model id.

Use the model in automations

Reference the model by the name you gave the record.

start:
  llm.chat/summarize:
    output: results
    inputs:
      model: anthropic-sonnet
      messages:
        0:
          role: user
          content: Summarize this conversation in one sentence.
  return:
    summary@key: results:content

commands:
  llm.chat:
    allow@bool: yes

The same record works with llm.agent: for tool-using conversations, and with llm.router: to pick between several models as data. An automation that doesn't name a model resolves a pool instead – a search across agent models rather than a named record. Omit a search entirely and you get every available model, in the priority order an admin set.

Anthropic doesn't offer embeddings, so there's no llm.embed: example here. Use a provider that does – OpenAI, Together AI, Hugging Face or Pinecone.

Resources

Guide: Summarize long ticket conversations
Guide: Update organization contact details from their website
Reference: Agent models