Real-time information synthesis, large codebases; prompts ≥ 200K tokens bill $4.00/$12.00
Stored values, not live provider measurements.
| Provider | xAI |
| Category | Flagship |
| Input cost / 1M tokens | $2.00 |
| Output cost / 1M tokens | $6.00 |
| Cache read / 1M tokens | $0.500 |
| Context window | 500k tokens |
| Max output | Not disclosed |
| Batch API | Not listed |
| Vision | Supported |
| Vision price / 1k images | Billed as tokens |
| Speed rating | Moderate |
| Intelligence score | 35/100 |
| Throughput | 72 tokens/sec |
| Time to first token | 43.00s |
| Hardware | Colossus cluster (not disclosed in detail) |
Enter your own input, output, caching, and batch assumptions in the calculator.
Open calculatorPricing review: 11/4/2026
Performance review: 11/4/2026
Grok 4.7 costs $2.000 per 1M input tokens and $6.000 per 1M output tokens in the stored catalog. Blended cost depends on your input/output mix.
Grok 4.7 has a context window of 500k tokens (500,000 tokens). This is the maximum combined input and output for a single request.
Grok 4.7 is currently offered by xAI. Pricing is a stored catalog value — confirm current rates with the provider.