Grok 4.20 Multi-Agent

Provider: xAI US Official API price

Input price
$1.25
/ 1M tokens
Output price
$2.50
/ 1M tokens
Cache price
$0.20
/ 1M tokens (read)
Context
2M tokens
Max output 1800K tokens

Overview

xAI's Grok 4.20 Multi-Agent is a reasoning variant designed for parallel agent workflows, deep research, and tool coordination.

Strengths

  • 2,000,000 token context window
  • 1,800,000 token maximum output
  • Native vision and JSON mode support
  • Cached input priced at $0.20 per million

Best use cases

  • Parallel multi-agent research tasks
  • Processing large codebases and repositories
  • Complex tool-use orchestration pipelines
  • Synthesizing massive document sets

Pricing position

Input matches Grok 4.3 and Grok 4.20 at $1.25/M with $2.50/M output, undercutting GPT-5's $10/M output rate.

Caveats

No free tier is available; use Grok Build 0.1 for cheaper baseline tasks.

Notes drafted by an LLM from the figures on this page (2026-11-13) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
1800K tokens
Knowledge cutoff
2025-09-01
Listed on OpenRouter
2026-03-31
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Image inputJSON outputReasoning

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.25
1M (small app) 1 0.5 $2.50
10M (mid scale) 10 5 $25.00
100M (large) 100 50 $250.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from xAI

Similar-priced models

Source: OpenRouter API (x-ai/grok-4.20-multi-agent)