All AI models · LLM benchmarks · Methodology

xAI

Grok 4.20 Multi-Agent

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

Model facts

Context window
2M tokens
Maximum output
2M tokens
Cheapest paid input
$1.25 per 1M tokens
Cheapest paid output
$2.5 per 1M tokens
Open weights
no
Providers
6

Capabilities and modalities

reasoning, tool calling, structured output, attachments, temperature control, text, image, pdf.

Observed price history

  • 2026-08-24: $1.25 input / $2.5 output per 1M tokens

API providers

  • OpenRouter — model id x-ai/grok-4.20-multi-agent; $1.25 input / $2.5 output per 1M tokens; provider documentation
  • Vercel AI Gateway — model id spacexai/grok-4.20-multi-agent; $1.25 input / $2.5 output per 1M tokens; provider documentation
  • xAI — model id grok-4.20-multi-agent-0309; $1.25 input / $2.5 output per 1M tokens; provider documentation
  • Venice AI — model id grok-4-20-multi-agent; $1.42 input / $2.83 output per 1M tokens; provider documentation
  • NanoGPT — model id x-ai/grok-4.20-multi-agent; $2 input / $6 output per 1M tokens; provider documentation
  • Poe — model id xai/grok-4.20-multi-agent; $2 input / $6 output per 1M tokens; provider documentation