Grok 4.6
by Venice AI · family grok · listed Aug 2026RTV
Grok model for agentic tool use, reasoning, coding, and live assistance
Current rates USD per 1M tokens
Input$2.27
Output$6.80
Cache read$0.57
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
grok-4-6- Context window
- 500K tokens
- Max output
- 200K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- Feb 2026
- Released
- 2026-08-10
- Last updated
- 2026-08-12
← All Venice AI listings