Grok 4.6
SpaceXAI's frontier model for coding, agentic tasks, and knowledge work, with a 500K-token context window, image input, and controllable reasoning effort.
Source: Grok 4.6 technical overview, xAI language models API, xAI reasoning documentation, xAI prompt caching documentation
Pricing
Every billing leg from the live catalog, in USD per 1M tokens.
| Billing leg | Rate |
|---|---|
| Input | $2 / M |
| Output | $6 / M |
| Cache read | $0.5 / M |
Cost calculator
Billing-grade math over the rate card above, including the thinking tokens most estimates miss.
Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.
Provider
Where this model runs, and what it charges.
| Platform | Input / M | Output / M | Cache read / M | Batch | Access |
|---|---|---|---|---|---|
xAI | $2 | $6 | $0.5 | — | First-party API |
Price history
Has this model gotten cheaper or more expensive?
| Effective | Input / Output | Status |
|---|---|---|
| August 12, 2026 – August 13, 2026 | $2 / $6 | past |
| August 13, 2026 | $2 / $6 | current |
More from xAI (Grok)
Other models from the same provider.
Stop estimating. Track it.
SuperPenguin meters every Grok 4.6 call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.
Rates are generated from SuperPenguin's live pricing catalog.