Grok 4.6

xAIMCP Tool CallReasoning

xai/grok-4.6Closed API

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

Benchmark Pricing$2.00 / 1M in$6.00 / 1M out$0.50 cache read

Context: 500,000 tokens•Max Output: 500,000 tokens•Knowledge: 2026-02-01•Released: 2026-08-12

TECHNICAL SPECIFICATIONS

Context Window500,000500K tokens

Max Output500,000500K tokens

LicenseProprietaryCloud API only

Input Modalities

TextVision

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Grok 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 500,000 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

CursorBenchscore

40.4

DeepSWEscore

65.2

EEBenchscore

AA-BriefcaseElo

1546

Terminal-Benchscore

20.3

Harvey Legal Agent Benchmarkscore

15.8

HealthBenchscore

48.5

GDPvalElo

1605

API CALL INVOCATION EXAMPLE

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

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

const response = await client.chat.completions.create({
  model: "xai/grok-4.6",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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