As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/grok-4-20/

# Grok 4.20 (Reasoning / Non-reasoning / Multi-Agent)

xAI, Grok 4 family. Status: legacy. Type: reasoning model. Released: 2026-03. Training cutoff: not published.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| xAI API | `grok-4.20-0309-reasoning` | https://api.x.ai/v1/chat/completions | https://docs.x.ai/docs/models |
| xAI API (non-reasoning) | `grok-4.20-0309-non-reasoning` | https://api.x.ai/v1/chat/completions |  |
| xAI API (multi-agent) | `grok-4.20-multi-agent-0309` |  | https://docs.x.ai/developers/model-capabilities/text/multi-agent |
| OpenRouter | `x-ai/grok-4.20` |  | https://openrouter.ai/x-ai/grok-4.20 |
| OpenRouter (multi-agent) | `x-ai/grok-4.20-multi-agent` |  | https://openrouter.ai/x-ai/grok-4.20-multi-agent |

## Pricing

- Input: $1.25 per 1M tokens
- Cached input: $0.20 per 1M tokens
- Output: $2.50 per 1M tokens
- Input, prompts over 200K tokens: $2.50 per 1M tokens
- Output, prompts over 200K tokens: $5 per 1M tokens
- Unit as published: per 1M tokens (USD)
- Source: https://docs.x.ai/docs/models
- Last checked: 2026-09-29

## Specs

- Input: text, image
- Output: text
- Context window: 1,000,000 tokens
- Max output: not published
- Open weights: no
- Licence: proprietary

## What it has not seen

- No published training cutoff. Counted from its release (2026-03): at least 1,889 AI events since (433 major, 85 historic), as of 2026-11-13.
- Everything since February 2026: https://postcutoff.com/since/2026-02/

## What stands out

- Multi-agent model variant: Dedicated API id that runs parallel collaborating agents (4 at low/medium effort, 16 at high/xhigh) that search and cross-check before synthesizing an answer. Source: https://docs.x.ai/developers/model-capabilities/text/multi-agent
- Reasoning and non-reasoning twin ids: Same snapshot (0309) offered as separate reasoning and non-reasoning model ids. Source: https://docs.x.ai/docs/models

## Notes

Snapshot ids dated 0309. xAI docs list 1M context; OpenRouter lists 2M. Superseded by Grok 4.5-4.7; logprobs unsupported.

Previous-generation Grok, notable for its multi-agent variant for deep research.

```bash
curl https://api.x.ai/v1/chat/completions -H "Authorization: Bearer $XAI_API_KEY" -H "Content-Type: application/json" \
 -d '{"model":"grok-4.20-0309-reasoning","messages":[{"role":"user","content":"Hello"}]}'
```

Sources: https://docs.x.ai/docs/models , https://docs.x.ai/developers/model-capabilities/text/multi-agent

Model page: https://postcutoff.com/m/grok-4-20/