Grok 4.20 Reasoning
by Vercel AI Gateway · family grok · listed Mar 2026RTV
Grok model for agentic tool use, reasoning, coding, and live assistance
Current rates USD per 1M tokens
Input$1.25
Output$2.50
Cache read$0.20
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
xai/grok-4.20-reasoning- Context window
- 2M tokens
- Max output
- 2M tokens
- Input modalities
- text, image, pdf
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-03-10
- Last updated
- 2026-03-23
← All Vercel AI Gateway listings