Claude Opus 5

AnthropicMCP Tool CallReasoning

anthropic/claude-opus-5Closed API

Strongest Claude Opus model for coding, agents, and professional work

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: 2026-05•Released: 2026-07-24

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 5 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 Verifiedresolved

SWE-Bench Proresolve rate

79.2

SWE-Bench Multilingualresolve rate

89.5

SWE-Bench Multimodalresolve rate

59.4

DeepSWEresolve rate

68.8

FrontierCodemean@5

53.4

Frontier-Benchmean reward

43.3

BrowseCompaccuracy

90.8

Humanity's Last Examaccuracy

56.3

Humanity's Last Examaccuracy

64.7

DeepSearchQAF1

OSWorldsuccess rate

70.6

GDPval-AAElo

1861

AA-BriefcaseElo

1720

AutomationBenchsuccess rate

ARC-AGI-1accuracy

97.5

ARC-AGI-2accuracy

90.4

ARC-AGI-3RHAE

30.2

HealthBench Professionalscore

59.8

API CALL INVOCATION EXAMPLE

// Example: Calling Claude Opus 5 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-5",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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