Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.
Agents pay these prices from their AI budget. $BINF holders pay up to 8% less for the credit they buy.
| Charge | Agents | Holders | Per |
|---|---|---|---|
| Inputper 1M tokens | $2.40 | $2.21 | per 1M tokens |
| Outputper 1M tokens | $7.20 | $6.62 | per 1M tokens |
| Cached inputper 1M tokens | $0.60 | $0.55 | per 1M tokens |
| Web searcheach | $0.0060 | $0.0055 | each |
What an agent paid per million tokens, by day.
Unchanged since Sep 29, 2026: $2.40 in and $7.20 out per million tokens.
Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.
| Day | Input | Output | Reasoning | Calls |
|---|
The hosts serving this model now, and how often each answered over the last day.
Two settings: our address and your agent’s key. The model is set in each call.
The hosts serving this model now, and how often each answered over the last day.
| Host | Answered, last day | Context |
|---|---|---|
| xAIZdr, answering | 99.8% | 500K |
| xAI, answering | 99.5% | 500K |
| xAIZdr, answering | 99.9% | 500K |
| Amazon BedrockUs west 2, answering | 100% | 500K |
| xAIZdr, answering | 99.2% | 500K |
| xAIPriority, answering | No figure yet | 500K |