Grok 4.20 (Non-Reasoning)

xAIMCP Tool Call
xai/grok-4.20-0309-non-reasoningClosed API

Grok model for agentic tool use, reasoning, coding, and live assistance

Benchmark Pricing$1.25 / 1M in$2.50 / 1M out$0.20 cache read
Context: 1,000,000 tokens•Max Output: 30,000 tokens•Released: 2026-03-09

TECHNICAL SPECIFICATIONS

Context Window1,000,0001M tokens
Max Output30,00030K tokens
LicenseProprietaryCloud API only
Input Modalities
TextVisionPDF
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Grok 4.20 (Non-Reasoning) 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.

API CALL INVOCATION EXAMPLE

// Example: Calling Grok 4.20 (Non-Reasoning) 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-4.20-0309-non-reasoning",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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

PRICING BY PROVIDER

11 providers
xAIgrok-4.20-0309-non-reasoning
$1.25 / $2.50$0.20 cache
OCI Generative AIxai.grok-4.20-non-reasoning
$1.25 / $2.50$0.20 cache
Tempr Gatewayxai/grok-4.20-0309-non-reasoning
$1.25 / $2.50$0.20 cache
Cloudflare AI Gatewayxai/grok-4.20-0309-non-reasoning
$2.00 / $6.00$0.20 cache
Eden AIxai/grok-4.20-0309-non-reasoning
$1.25 / $2.50$0.20 cache
Merge Gatewayxai/grok-4.20-0309-non-reasoning
$1.25 / $2.50$0.20 cache
Azure Cognitive Servicesgrok-4-20-non-reasoning
$2.00 / $6.00
Vertexxai/grok-4.20-non-reasoning
$1.25 / $2.50$0.20 cache
DevPass (LLM Gateway)grok-4-20-beta-0309-non-reasoning
$2.00 / $6.00$0.20 cache
Azuregrok-4-20-non-reasoning
$2.00 / $6.00
Impossiblxai/grok-4.20-0309-non-reasoning
$1.25 / $2.50$0.20 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.20 / 1M tokens, saving up to 84% on repetitive MCP tool definitions and system instructions.

MODEL RESOURCES