Skip to main content

​
Anthropic

Use Anthropic’s Claude models with RadarOS through the unified ModelProvider interface. Claude excels at long-context tasks, analysis, and nuanced reasoning.

​
Setup

Install the Anthropic SDK (required by RadarOS for Anthropic support):
npm install @anthropic-ai/sdk

​
Factory

import { anthropic } from "@radaros/core";

const model = anthropic("claude-sonnet-4-20250514");
​
modelId
string
required
The Anthropic model identifier.
​
config
object
Optional configuration. See Config below.

​
Supported Models

Model IDDescription
claude-sonnet-4-20250514Claude Sonnet 4. Strong balance of speed and capability.
claude-3-5-haiku-20241022Claude 3.5 Haiku. Fast, cost-effective.
Pass any valid Anthropic model ID to the factory. Check the Anthropic docs for the latest model IDs.

​
Config

​
apiKey
string
Anthropic API key. If omitted, uses ANTHROPIC_API_KEY environment variable.

​
Example

const model = anthropic("claude-sonnet-4-20250514", {
  apiKey: process.env.ANTHROPIC_API_KEY,
});

​
Multi-Modal Support

Anthropic Claude supports images and files/documents as input. Audio is not supported.

​
Images

Pass images as base64 or URL in ContentPart[]: 
const result = await agent.run([
  { type: "text", text: "What's in this image?" },
  { type: "image", data: "https://example.com/photo.jpg", mimeType: "image/jpeg" },
]);

​
Files & Documents

PDF and other documents can be sent via URL or base64. Anthropic processes them natively as document blocks: 
const result = await agent.run([
  { type: "text", text: "Summarize this PDF." },
  { type: "file", data: "https://example.com/report.pdf", mimeType: "application/pdf", filename: "report.pdf" },
]);
Both URL-based and base64-encoded files are supported. The provider auto-detects the format.

​
Unsupported: Audio

Audio input is not supported by Anthropic. If passed, the provider logs a warning and substitutes a placeholder text block.

​
Reasoning / Extended Thinking

Claude supports extended thinking — the model “thinks” step-by-step before responding. Enable it via the reasoning config on your agent: 
import { Agent, anthropic } from "@radaros/core";

const agent = new Agent({
  name: "deep-thinker",
  model: anthropic("claude-sonnet-4-6"),
  instructions: "Solve problems step by step.",
  reasoning: {
    enabled: true,
    budgetTokens: 4000, // Max tokens for thinking (not shown to user)
  },
});

const result = await agent.run(
  "A farmer has 17 sheep. All but 9 run away. How many does he have left?"
);

console.log(result.thinking);
// "Let me parse this carefully... 'all but 9 run away' means 9 remain..."
console.log(result.text);
// "The farmer has 9 sheep left."
When reasoning is enabled, maxTokens is automatically adjusted. If your maxTokens is lower than budgetTokens + 4096, it’s overridden to ensure room for both thinking and response. See Reasoning for details.

​
Prompt Caching

Anthropic automatically caches prompt prefixes for repeated conversations. This reduces cost and latency when the system prompt or conversation history is reused across requests. No configuration is needed — the SDK handles this transparently. Benefits are most significant when:
  • System prompts are long (e.g., detailed instructions, few-shot examples)
  • Conversations span many turns (the prefix is cached across requests in the same session)
  • Multiple users share the same agent instructions

​
Full Example

import { Agent, anthropic } from "@radaros/core";

const agent = new Agent({
  name: "Claude Assistant",
  model: anthropic("claude-sonnet-4-20250514", {
    apiKey: process.env.ANTHROPIC_API_KEY,
  }),
  instructions: "You are a thoughtful, thorough assistant. Think step by step.",
});

const output = await agent.run("Analyze the pros and cons of microservices.");
console.log(output.text);