Grok 4.7 API pricing
Grok 4.7 is a flagship model from xAI Grok with a 500,000-token context window. Rates below are per 1,000,000 tokens, verified November 2026.
Price list
| Token class | Rate / 1M | Notes |
|---|---|---|
| Input | $2 | Prompt tokens not served from cache |
| Cached input | $0.50 | 75% below base input |
| Cache write | — | Not billed per token |
| Output | $6 | 3.0× the input rate |
| Long context input | $4 | Above 200,000 input tokens |
| Long context output | $12 | Same threshold |
| Batch API | −50% | Input and output, results within 24 h |
Current xAI flagship at the same list price as Grok 4.6. Prompts above 200K tokens double every rate.
What Grok 4.7 costs at three real workloads
Sticker prices rarely match the invoice. These three workloads use the rates above, with cache writes charged once per job and the batch discount applied only where the provider offers it.
| Workload | Requests | Tokens | Estimated cost |
|---|---|---|---|
| Support chat | 1,000 | 4K in / 600 out | $11.60 |
| RAG with caching | 1,000 | 50K in (45K cached) / 1K out | $38.57 |
| Nightly batch job | 10,000 | 10K in / 2K out | $160 |
Caching the 45K-token prefix saves about 64% on the RAG workload versus sending it uncached every call ($106 → $38.57). Batch mode halves the nightly job.
Where Grok 4.7 sits in the market
Out of 45 models in this dataset, Grok 4.7 ranks #36 cheapest by input rate, #24 by output rate, and #25 on a blended 1M-input-plus-250K-output workload.
| Model | Provider | Input | Output | Blended |
|---|---|---|---|---|
| Grok 4.7 | xAI Grok | $2 | $6 | $3.50 |
| Grok 4.6 | xAI Grok | $2 | $6 | $3.50 |
| Gemini 2.5 Pro | Google Gemini | $1.25 | $10 | $3.75 |
| Gemini 4 Hydrogen | Google Gemini | $1.50 | $7.50 | $3.38 |
Blended cost = 1M input tokens + 250K output tokens at list price.
FAQ
How much does Grok 4.7 cost per 1M tokens?
$2 per 1M input tokens and $6 per 1M output tokens on the standard tier, rising to $4 / $12 above 200,000 input tokens.
Is prompt caching cheaper on Grok 4.7?
Yes. Cached input bills at $0.50 per 1M tokens, 75.0% below the $2 base input rate, with no separate cache-write rate published.
Does Grok 4.7 support the Batch API?
Yes. Batch requests bill at roughly half the standard input and output rates: the nightly job above costs $320 at list price and about $160 in batch mode.
Keep reading
- All xAI Grok models and rates
- Every model in the dataset, ranked by price
- Grok 4.6 vs Grok 4.7
- GPT-6 Astra vs Grok 4.7
- Claude Fable 5.1 vs Grok 4.7
- Calculate your own monthly cost with the free estimator
Run these numbers in the calculator