Model Details
Where is Grok-4.7 a perfect fit?
- Long-running software engineering tasks
- Autonomous coding agents
- Repository-scale code analysis and modification
- Complex knowledge-work workflows
- Multi-step tool calling
- Technical research and investigation
- Image-assisted reasoning and analysis
- Professional automation requiring sustained reasoning
- Agentic applications requiring configurable reasoning effort
Grok 4.7 is primarily an agentic coding and knowledge-work upgrade. xAI emphasizes longer reasoning runs, self-verification, and performance on tasks that can take hours rather than optimizing solely for short conversational responses.
Quick Model Estimate
Your Grok-4.7 Cost Estimate
💰 Total Cost
—
for 1000 input + 1000 output tokens
Cost Breakdown
Prices are watched for changes and checked against the provider's own page.
Pricing
|
Provider
↕
|
Modality
↕
|
Service Tier
↕
|
Input Price
(per 1M tokens) ↕ |
Output Price
(per 1M tokens) ↕ |
Cached Input
(per 1M tokens) ↕ |
Context Size
↕
|
View
|
|---|---|---|---|---|---|---|---|
 Perplexity | Text | Standard | $2.0000 | $6.0000 | $0.5000 | Up to 199,999 tokens | → |
| Perplexity | Text | Standard | $4.0000 | $12.0000 | $1.0000 | 200,000+ tokens | → |
Benchmarks
Scores from standardized evaluations by Artificial Analysis and Design Arena. Higher is better — the indices summarize overall ability, while the detailed scores break down performance on individual benchmarks.
Artificial Analysis
Higher is better · benchmarked by Artificial AnalysisExpert-level questions across many academic domains
Unpublished physics research reasoning problems
Long-context reasoning across large inputs
Research-level scientific coding tasks
Economically valuable, real-world knowledge work
Breadth of factual knowledge across domains
How reliably the model avoids fabricated answers
| Variant | Humanity's Last Exam | AA-LCR | SciCode | CritPt | GDPval | Omniscience Accuracy | Omniscience Non-Hallucination |
|---|---|---|---|---|---|---|---|
| Grok 4.7 (Xhigh) | 43.1% | 76.7% | 57.4% | 17.7% | 61.1% | 47.4% | 70.7% |
| Grok 4.7 (High) | 42.3% | 77% | 57.8% | 18% | 60.8% | 47.8% | 67.6% |
| Grok 4.7 (Low) | 39.2% | 80% | 54.9% | 13.4% | 54.6% | 49.7% | 60.1% |
Design Arena
Elo rating by arena & category| Variant | Arena | Category | Elo | Win % | Percentile | Avg time (ms) |
|---|---|---|---|---|---|---|
| grok-4.7 | models | 3d | 1,273 | 48.4% | 83 | 861,386 |
| grok-4.7 | models | codecategories | 1,270 | 47.8% | 79 | 803,966 |
| grok-4.7 | models | dataviz | 1,235 | 45.9% | 69 | 557,502 |
| grok-4.7 | models | gamedev | 1,313 | 52.6% | 89 | 1,067,872 |
| grok-4.7 | models | uicomponent | 1,274 | 48.9% | 79 | 768,347 |
| grok-4.7 | models | website | 1,252 | 46% | 73 | 739,020 |
Compare Grok-4.7 with
Two models side by side: worked costs, every rate, and every benchmark figure both of them report.
FAQs about Grok-4.7
How much does Grok-4.7 cost per 1M tokens?
Grok-4.7 costs between $2.00 and $4.00 per million input tokens, and between $6.00 and $12.00 per million output tokens.
What does a typical workload cost with Grok-4.7?
1,000 requests of 2,000 input and 500 output tokens each — 2,000,000 input and 500,000 output tokens in total — costs $7.00 with Grok-4.7 at its lowest rates. Use the calculator on this page for your own volumes.
Where can I use Grok-4.7?
Grok-4.7 is available through Perplexity, from $2.00 per million input tokens.
What is Grok-4.7's context window?
Grok-4.7 has a context window of 500,000 tokens.
What input types does Grok-4.7 support?
Grok-4.7 accepts text, image and file input, and returns text.
What is Grok-4.7's knowledge cutoff?
Grok-4.7's training data runs to 31 May 2026. It has no built-in knowledge of events after that date.