Claude Opus 4.6

AnthropicMCP Tool CallReasoning

anthropic/claude-opus-4-6Closed API

High-end Claude for difficult coding, planning, and slower expert reasoning

Benchmark Pricing$5.00 / 1M in$25.00 / 1M out$0.50 cache read

Context: 1,000,000 tokens•Max Output: 128,000 tokens•Knowledge: 2025-05-31•Released: 2026-02-05

TECHNICAL SPECIFICATIONS

Context Window1,000,0001M tokens

Max Output128,000128K tokens

LicenseProprietaryCloud API only

Input Modalities

TextVisionPDF

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Claude Opus 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-Bench Proresolve rate

51.9

SWE-Atlas Codebase QnAscore

33.3

SWE-Atlas Codebase QnAscore

SWE-Atlas Refactoringscore

35.58

SWE-Atlas Test Writingscore

36.67

SWE-Atlas Test Writingscore

36.08

Artificial Analysis Coding Agent Indexaverage pass@1

51.3

SWE-Atlas Codebase QnApass@1

71.9

SWE-Bench Propass@1

11.8

Terminal-Benchpass@1

70.2

API CALL INVOCATION EXAMPLE

// Example: Calling Claude Opus 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-opus-4-6",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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