Loading…
xAI
x-ai/grok-4.6
Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).
Only tracked on Vercel AI Gateway.
Vercel AI Gateway share of tokens, by day.
Grok 4.6 holds 1.14% today, up from 0.10% at the start of the visible window.
Grok 4.6's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-10-15, Grok 4.6 holds 0.0% of Vercel AI Gateway token share, down 0.39pp over 30 days. Data: Vercel AI Gateway as of 2026-10-15. tidelines.ai
Where to run it
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
Grok 4.6 is served by 4 tracked endpoints on OpenRouter. The cheapest output price is $6.00 per million tokens from xAI · 500k, and the most expensive is $12.00 from xAI · 500k. The largest context window offered is 500k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| xAI · 500k | $2.00 | $6.00 | 500k | 100.00% |
| xAI · 500k | $2.20 | $6.60 | 500k | — |
| Amazon Bedrock | $2.20 | $6.60 | 500k | — |
| xAI · 500k | $4.00 | $12.00 | 500k | 100.00% |
Median dollars spent on one Grok 4.6 session, by coding agent and session length.
Token rate sets the price; session length and reasoning set the bill.
| Agent | 1 turn | 2–9 turns | 10–49 turns | 50+ turns |
|---|---|---|---|---|
| Claude Code | — | $0.148 | $1.33 | — |
| Hermes Agent | $0.010 | $0.132 | $0.994 | $5.92 |
