---
title: Chat Anthropic
description: Connect an Anthropic Claude chat model to AI nodes.
---

Give an AI node access to Anthropic's Claude models, using your own Anthropic API key.

Pick a saved connection in the **Authentication** field, or create one from there.

## What it does

Chat Anthropic is a model you plug into the **Model** slot of an AI node, such as the [Tools Agent](/nodes/builtin/ai/aiagents/toolsagentnode/) or [Basic LLM Chain](/nodes/builtin/ai/aiagents/basicllmchainnode/). It does not run on its own and has no output. When the AI node runs, it sends its messages to Anthropic with your key and gets Claude's reply back.

* **Temperature** is 0 when you leave it empty, so answers are focused and repeatable.
* Replies are capped at **Max Tokens** (4096 by default).
* A failed request is retried up to **Max Retries** times (2 by default). A request that gets no answer within 60 seconds fails.
* The long, stable start of each conversation is cached on Anthropic's side, which makes repeated calls in a long agent run cheaper.

## When to use it

* You want Claude for writing, careful reasoning or long documents.
* You want an agent that calls tools: connect it to the [Tools Agent](/nodes/builtin/ai/aiagents/toolsagentnode/).
* You already pay for Anthropic and want to use that account.

For a free, private model that runs on your device, use [Web LLM](/nodes/builtin/ai/aidependencies/llm/wbellm/) or [Ollama](/nodes/builtin/ai/aidependencies/llm/ollama/) instead.

## Inputs and settings

Type the **Model** id exactly as Anthropic lists it in its model documentation (for example a `claude-...` id). A display name such as "Claude Sonnet" is not accepted.

## Outputs

This node has no output port. It plugs into a slot on another node instead of passing items along.

* **Model** slot of [Tools Agent](/nodes/builtin/ai/aiagents/toolsagentnode/), [Q\&A Agent](/nodes/builtin/ai/aiagents/qanode/), [RAG Agent](/nodes/builtin/ai/aiagents/ragnode/), [Basic LLM Chain](/nodes/builtin/ai/aiagents/basicllmchainnode/), [Indexer](/nodes/builtin/ai/aiagents/indexernode/), [Text Classifier](/nodes/builtin/ai/aiagents/textclassifiernode/), [Sentiment Analysis](/nodes/builtin/ai/aiagents/sentimentanalysisnode/), [Summarization](/nodes/builtin/ai/aiagents/summarizationchainnode/), [Information Extractor](/nodes/builtin/ai/aiagents/informationextractornode/), [Guardrails](/nodes/builtin/ai/aiagents/guardrails/), [Auto-fixing Output Parser](/nodes/builtin/ai/aidependencies/outputparser/autofixingoutputparser/)

The AI node you connect it to produces the output. Chat Anthropic only decides which model answers.

## Dependencies and credentials

* **Authentication** (connection): required. See [Connect Anthropic](/app/connections/anthropic/).

In **Authentication**, save your Anthropic API key. Create one on the API keys page of the Anthropic Console, then add it as a credential in AWFlow (a Bearer Token or JWT Token credential both work; put only the key in it). See [Create a credential](/app/connections/create/).

## Example workflow

1. A [Context Menu](/nodes/builtin/trigger/contextmenu/) trigger on selected text.
2. [Basic LLM Chain](/nodes/builtin/ai/aiagents/basicllmchainnode/) with **Prompt** `Explain this in plain words, in 3 sentences: {{ $input.selectionText }}`.
3. Chat Anthropic in its **Model** slot, with your Claude model id and your Anthropic credential.
4. [Browser Notification](/nodes/extension/browsernotification/) with **Message** `{{ $input.response }}`.

## Common issues

* **"Model parameter is required and cannot be empty".** Fill in **Model** with an Anthropic model id.
* **An authentication error (401).** The key is wrong, revoked, or the credential holds something else. Create a new key in the Anthropic Console and update the credential.
* **A "model not found" error.** The model id is misspelled or retired. Copy a current id from Anthropic's model list.
* **The answer stops mid-sentence.** It hit **Max Tokens**. Raise it under **Options**.
* **The request times out.** Anthropic did not answer within 60 seconds. Try again, or use a faster model.

## Related nodes

* [Basic LLM Chain](/nodes/builtin/ai/aiagents/basicllmchainnode/): send one prompt and get a reply.
* [Tools Agent](/nodes/builtin/ai/aiagents/toolsagentnode/): an agent that can use tools and memory.
* [Chat OpenRouter](/nodes/builtin/ai/aidependencies/llm/openrouter/): reach Claude and many other models with one key.
* [Chat OpenAI](/nodes/builtin/ai/aidependencies/llm/openai/): OpenAI's GPT models.