xAI · Released Sep 21, 2026
Grok 4.7
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...
- Top 12%Vending-Bench 2
- Top 14%WebDev Arena
- Top 16%SciCode
- Top 21%GPQA Diamond
- Released
- Sep 21 2026
- Context window
- 500K 450K out
- Input / 1M tokens
- $2.00
- Output / 1M tokens
- $6.00
Where to run it
Providers
Cheapest: xAI at $2.00 / $6.00 per 1M input / output tokens — 50% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| xAI | $2.00 | $6.00 | $0.50 | 500K | 450K | 99.9%24h | Cheapest |
| xAIzdr | $2.00 | $6.00 | $0.50 | 500K | 450K | 99.3%24h | Cheapest |
| xAIzdr/us | $2.20 | $6.60 | $0.55 | 500K | 450K | 98.9%24h | +10% |
| xAIzdr/priority | $4.00 | $12.00 | $1.00 | 500K | 450K | 100%24h | +100% |
| xAIpriority | $4.00 | $12.00 | $1.00 | 500K | 450K | — | +100% |
Value
Price vs. performance
Grok 4.7 Other xAI Other labs Value frontier · GPQA Diamond vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
22 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| FrontierSWESoftware engineering · Ultra-long-horizon engineering tasks with a 20-hour budget each | 29.5% | #11of 19 | GPT-6 Astra65.5% |
| CursorBenchSoftware engineering · Ambiguous multi-file tasks drawn from real Cursor sessions | 46.3% | #7of 16 | Claude Opus 5.557.8% |
| FrontierCodeSoftware engineering · Mergeable fixes for hard open-source issues | 47.6% | #10of 41 | Claude Opus 5.554.6% |
| SciCodeSoftware engineering · Research-coding problems from the natural sciences | 57.8% | #14of 93 | Claude Opus 5.566.9% |
| WeirdML v3Software engineering · Unfamiliar ML and data tasks with vague goals | 8.5% | #12of 22 | GPT-6 Astra42.2% |
| APEX-AgentsAgents & computer use · Long professional tasks in banking, consulting and law | 54.6% | #19of 51 | Gemini 4 Argon82.4% |
| Vending-Bench 2Agents & computer use · Run a simulated vending business for a year (final balance) | $10,537 | #7of 61 | GPT-6 Astra$15,515 |
| GDP.pdfWriting & content · Answer questions about real professional PDFs | 22.8% | #19of 38 | GPT-6.1 Sol35.0% |
| SimpleQA VerifiedWriting & content · Factual accuracy on 1,000 short questions | 56.0% | #19of 66 | Gemini 4 Argon76.0% |
| WebDev ArenaDesign & visual · People vote on which model builds the better website (Elo) | 1638 | #12of 88 | Claude Opus 5.51820 |
| Blueprint-Bench 2Design & visual · Turn apartment photos into 2D floor plans | 32.5% | #14of 32 | Gemini 4 Argon54.4% |
| Furniture AssemblyDesign & visual · Spot mistakes in photos of IKEA builds | 20.8% | #32of 34 | Claude Opus 5.583.3% |
| GPQA DiamondReasoning & knowledge · PhD-level biology, chemistry and physics questions | 92.7% | #19of 92 | Gemini 4 Argon96.4% |
| ARC-AGI-2Reasoning & knowledge · Few-shot abstract reasoning on grid puzzles | 61.4% | #27of 63 | GPT-6 Astra95.0% |
| ARC-AGI-1Reasoning & knowledge · Pattern induction from input–output examples | 90.2% | #30of 63 | Gemini 4 Argon98.5% |
| CritPtReasoning & knowledge · Open-ended, research-level physics problems | 18.0% | #29of 96 | GPT-5.6 Sol32.3% |
| Chess PuzzlesReasoning & knowledge · Find the single best move in 100 new puzzles | 41.0% | #35of 70 | GPT-6 Astra76.0% |
| LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts | 49.4% | #27of 96 | Claude Sonnet 5.568.3% |
| FrontierMathMaths · Expert-written problems, undergrad to early research (tiers 1–3) | 53.0% | #50of 72 | GPT-6.1 Sol93.7% |
| FrontierMath Tier 4Maths · Exceptionally hard research-level problems | 17.1% | #48of 62 | GPT-6.1 Sol100.0% |
| ProofBenchMaths · Graduate maths proofs verified in Lean 4 | 26.0% | #46of 70 | Claude Sonnet 5.5100.0% |
| OTIS Mock AIMEMaths · Competition-style problems harder than MATH Level 5 | 98.1% | #25of 90 | Gemini 4 Argon100.0% |
Specs
Details
- Model ID
x-ai/grok-4.7- Developer
- xAI
- Release date
- Sep 21, 2026 ·
- Context window
- 500,000 tokens
- Max output
- 450,000 tokens
- API price
- $2.00 / $6.00 per 1M input / output tokens
- Providers
- 1
- Input types
- text, image, file
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- No
- Free tier
- No
Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.