Model registry / xAI / Grok / Grok 4.20 Multi-Agent
Grok 4.20 Multi-Agent
Grok model for agentic tool use, reasoning, coding, and live assistance
Line
Grok
Weights
API only
Released
2026-03-09
Context
1M
Input
$1.25 / 1M
Output
$2.50 / 1M
Max output
30K
Coverage
not covered yet
Overview
Grok 4.20 Multi-Agent is a Grok model from xAI, described for agentic tool use, reasoning, coding, and live assistance. It is part of the grok line and was released on 2026-03-09, following the non-reasoning Grok 4.20. It has a context window of 1,000,000 tokens and a maximum output of 30,000 tokens. It supports reasoning mode but not tool calling. It accepts image, PDF, and text inputs and returns text. The weights are not open. Pricing starts at $1.25 per million input tokens and $2.50 per million output tokens, with cached input at $0.20 per million tokens.
Specs
Pricing
First version of its line in the registry.
Strengths
- 1 million token context window
- 30,000 token max output
- Reasoning mode enabled
- Accepts image, PDF, and text
- Returns text output
Best for
- Reach for it for reasoning over million-token contexts
- Reach for it for coding with large codebases
- Reach for it for analyzing images and PDFs
- Reach for it for live assistance with multimodal inputs
How to access
1 host serve this model at the price above · the maker's documentation
Grok: every version
The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.
FAQ
- What is the context window?
- The context window is 1,000,000 tokens.
- Does it support tool calling?
- No, tool calling is not supported.
- What is the price?
- Input is $1.25 per million tokens, output is $2.50 per million, cached input is $0.20 per million.