xAI · LLMs & Coding

Grok 4.20 Multi-Agent

Catalog data · checked Nov 16, 2026

Grok 4.20 Multi-Agent is a language model from xAI, released in March 2026. It reads text, images and PDF files and writes text, with a context window of 1M tokens and up to 30K output tokens per answer. It costs $1.25 per million input tokens and $2.5 per million output tokens. That puts it in the upper price range: 54% of the 185 paid language models we track cost less.

Calculate my costCompare

Input price$1.25per 1M tokens
Output price$2.5per 1M tokens
Context window1Mtokens per request
Max output30Ktokens per answer
ReleasedMar 20268 months ago
WeightsClosedAPI only

What it can do

  • Tool calling
  • Structured output
  • Reasoning mode
  • Image input
  • File input
  • Audio input
  • Video input
  • Image output
  • Audio output
  • Prompt caching

More prices

Cached input (read)$0.2 /1M
Above 200K input tokens$2.5 in · $5 out

What it costs in practice

1,000 support replies1,000 chats with 800 input and 250 output tokens each$1.63
Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out$0.193
10,000 product descriptions300 input and 200 output tokens per text$8.75
One day of agentic codingabout 3M input and 150K output tokens across many calls$4.13

Calculated from the list prices above. Your bill depends on your real token counts. Use your own numbers →

Compare Grok 4.20 Multi-Agent with

Questions & answers

How much does Grok 4.20 Multi-Agent cost?

Grok 4.20 Multi-Agent costs $1.25 per 1 million input tokens and $2.5 per 1 million output tokens (USD, list price checked Nov 16, 2026).

How large is the context window of Grok 4.20 Multi-Agent?

Grok 4.20 Multi-Agent can process up to 1,000,000 tokens per request and return up to 30,000 tokens. As a rule of thumb, 1,000 tokens are about 750 English words.

Does Grok 4.20 Multi-Agent support tool calling?

No tool calling is listed for this model in the catalog.

Can Grok 4.20 Multi-Agent read images?

Yes, image input is supported, as well as file input (for example PDFs).