Skip to main content
Anthropic builds reliable, interpretable AI systems. Claude, their AI assistant, excels at thoughtful dialogue, content creation, complex reasoning, and coding. Cargo’s native integration with Anthropic allows you to use Claude models directly in your workflows.

​
How to set up Anthropic

You can use Anthropic in two ways:
  1. Cargo credits – Use Claude through Cargo’s managed integration
  2. Your own API key – Connect your Anthropic account

​
Connection details

FieldDescription
API KeyYour Anthropic API key
Find your API key in the Anthropic Console under API Keys.

​
Anthropic actions

​
Instruct

Send a prompt to a Claude model and receive a text response. Use cases
  • Content generation – Generate personalized emails and messages
  • Classification – Categorize text into predefined categories
  • Summarization – Summarize long documents or conversations
  • Data extraction – Extract structured information from text
  • Analysis – Analyze sentiment, intent, or other properties
  • Reasoning – Complex multi-step problem solving
Configuration
FieldDescription
ModelSelect the Claude model to use
PromptThe prompt to send to the model
System promptOptional system instructions
Maximum tokensLimit output length
TemperatureControl randomness (0-1)
With web searchEnable web search capabilities

​
Available models

The most powerful Claude model for complex and creative tasks with reasoning capabilities.Best for: Complex reasoning, advanced coding, creative tasksCredit cost: ~2 credits per 1,000 tokens
Premium model supporting images with advanced reasoning.Best for: Complex multi-modal tasks, detailed analysisCredit cost: ~2 credits per 1,000 tokens
Most intelligent model for building agents and coding.Best for: Agentic tasks, coding, complex reasoningCredit cost: ~0.2 credits per 1,000 tokens
Premium model with exceptional reasoning capabilities.Best for: Balanced performance, everyday complex tasksCredit cost: ~0.2 credits per 1,000 tokens
High-performance model supporting images.Best for: Multimodal tasks, detailed analysisCredit cost: ~0.2 credits per 1,000 tokens
Fast inference model optimized for speed.Best for: High-volume, low-latency tasksCredit cost: ~0.2 credits per 1,000 tokens
Recommended model: Claude Sonnet 4 offers excellent performance for most use cases with reasonable cost.

​
Advanced settings

​
System prompt

Set instructions that guide Claude’s behavior:
  • Define the model’s role or persona
  • Set output format guidelines
  • Provide context about your use case
  • Establish constraints or rules

​
Temperature

Control the randomness of outputs:
TemperatureBehavior
0Most deterministic
0.3-0.5Balanced
0.7-1More creative, varied
Enable Claude to search the web for current information:
  • Real-time data lookups
  • Current events research
  • Fact verification