Claude Sonnet 4.6

AnthropicMCP Tool CallReasoning

anthropic/claude-sonnet-4-6Closed API

Claude workhorse for coding agents, careful analysis, and production cost control

Benchmark Pricing$3.00 / 1M in$15.00 / 1M out$0.30 cache read

Context: 1,000,000 tokens•Max Output: 64,000 tokens•Knowledge: 2025-08-31•Released: 2026-02-17

TECHNICAL SPECIFICATIONS

Context Window1,000,0001M tokens

Max Output64,00064K tokens

LicenseProprietaryCloud API only

Input Modalities

TextVisionPDF

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Claude Sonnet 4.6 natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 1,000,000 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.

STANDARDIZED BENCHMARKS & EVALS

SWE-Atlas Codebase QnAscore

31.2

SWE-Atlas Refactoringscore

32.21

SWE-Atlas Test Writingscore

31.76

Artificial Analysis Coding Agent Indexaverage pass@1

49.4

SWE-Atlas Codebase QnApass@1

70.3

SWE-Bench Propass@1

14.9

Terminal-Benchpass@1

63.1

Terminal-Benchsuccess rate

Humanity's Last Examaccuracy

34.6

Humanity's Last Examaccuracy

46.8

OSWorld-Verifiedsuccess rate

78.5

API CALL INVOCATION EXAMPLE

// Example: Calling Claude Sonnet 4.6 via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ANTHROPIC_API_KEY,
});

const response = await client.chat.completions.create({
  model: "anthropic/claude-sonnet-4-6",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);