SDK Configuration

Step 3: Select your AI provider and model.

Agent Workshop supports two AI providers. Each has different strengths, pricing, and model options.

Claude Agent SDK (Recommended)

The Claude Agent SDK is Anthropic's official framework for building AI agents. It's the recommended choice for most use cases.

Available Models

ModelContextPricing (Input/Output)Best For
Claude Sonnet 4.5200K tokens$3 / $15 per millionGeneral use, best balance of cost and capability
Claude Haiku 4.5200K tokens$1 / $5 per millionFast, cost-effective tasks
Claude Opus 4.1200K tokens$15 / $75 per millionComplex reasoning, highest capability

Advantages

  • Native streaming support for real-time responses
  • Built-in file operation tools
  • Optimized for agentic workflows
  • Simple setup process

Setup Requirements

  1. Create an account at console.anthropic.com
  2. Generate an API key
  3. Set ANTHROPIC_API_KEY in your .env file

OpenAI Agents SDK

The OpenAI Agents SDK provides agent capabilities with function calling and tool use.

Available Models

ModelContextBest For
GPT-5.1128K tokensLatest capabilities, general use
GPT-5 mini128K tokensCost-effective, faster responses
GPT-4.1128K tokensStable, well-tested

Advantages

  • Official OpenAI agent framework
  • Advanced function calling
  • Streaming support
  • Wide ecosystem compatibility

Setup Requirements

  1. Create an account at platform.openai.com
  2. Generate an API key
  3. Set OPENAI_API_KEY in your .env file

Which should I choose?

Both providers produce functionally similar agents. Choose based on:

  • Your preferred AI provider
  • Existing API keys you have
  • Specific model capabilities you need
  • Pricing considerations

Advanced Settings

Max Tokens

Controls the maximum length of agent responses. Range: 1,000 - 8,000 tokens. Default: 4,096 tokens.

  • Lower values (1,000-2,000) - Concise responses, faster, cheaper
  • Higher values (6,000-8,000) - Detailed responses, better for complex tasks

Temperature

Controls response randomness. Range: 0.0 - 1.0. Default: 0.7.

  • Lower values (0.0-0.3) - Deterministic, consistent, best for code/analysis
  • Higher values (0.7-1.0) - Creative, varied, best for content generation

Recommended settings

For most agent use cases, the defaults work well. Consider lowering temperature to 0.3 for code-focused agents where consistency matters.