Skip to main content

Anthropic

Anthropic LLM, also known as Claude, is a large language model focused on safety and helpfulness. It can generate text, answer questions, and perform many other tasks with a focus on avoiding harmful or misleading outputs.

Extended Thinking Support

Anthropic now supports Extended Thinking capabilities with step-by-step transparency!

Key Features:

  • ✅ Enable Extended Thinking: Enhance reasoning for complex tasks with transparent thought processes
  • 🎯 Thinking Budget Tokens: Configure the maximum tokens for Claude's internal reasoning
  • 🔍 Step-by-step Transparency: See how Claude approaches complex problems
  • ⚠️ Cost Impact: Extended thinking consumes additional tokens, increasing usage costs
  • 📋 Availability: Available for Claude 3.7 Sonnet and newer versions

Getting started with Anthropic​

  1. Sign up for an Anthropic account..

  2. Purchase credits.

  3. Create an API key as shown below.

    img Anthropic Embeddings Configuration

    img Anthropic Embeddings Configuration

    img Anthropic Embeddings Configuration

    img Anthropic Embeddings Configuration

  4. Select a plan or claim the free $5 credits.

    img Anthropic Embeddings Configuration

Setting up the Anthropic LLM model in Unstract​

Now that we have an API key from Anthropic, we can use it to set up an LLM profile on the Unstract platform. For this:

  • Sign in to the Unstract Platform
  • From the side navigation menu, choose Settings 🞂 LLMs
  • Click on the New LLM Profile button.
  • From the list of LLMs, choose Anthropic. You should see a dialog box where you enter details.
Extended Thinking Configuration

If you're using Claude 3.7 Sonnet or newer versions, you'll have additional options:

Enable Extended Thinking

  • ☑️ Check this option to activate enhanced reasoning with step-by-step transparency
  • Available for Claude 3.7 Sonnet and newer model versions

Thinking Budget Tokens

  • 🎯 Token Budget: Set the maximum tokens for Claude's internal reasoning
  • 💡 Recommendation: Start with 3000 tokens for most use cases
  • 📈 Higher Budget: More tokens = more detailed reasoning but increased costs

⚠️ Important: Extended thinking consumes additional tokens, which will increase your usage costs

img Google Anthropic LLM Configuration

  • For Name, enter a name for this connector.
  • In the Model Name enter the Anthropic LLM model. To get the Anthropic model names, refer Anthropic Models Section
  • Leave the Max retries and Timeout fields to their default values.
  • In the API Key field, paste the API key we created on the Anthropic website.
  • For Claude 3.7 Sonnet and newer: Enable extended thinking and set your preferred thinking budget tokens
  • Click on Test Connection and ensure it succeeds. You can finally click on Submit and that should create a new LLM Profile for use in your Unstract projects.