Grok 4.7 Official Specifications, Pricing & Benchmarks
Latest xAI Grok 4.7 flagship with 500K context and 500K max output tokens ($2/$6).
📋 Grok 4.7 Official API & System Card Specifications
Verified against official xAI developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- grok-4.7
- Release Date
- 2026-09-21
- Weight License
- Proprietary (Undisclosed)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- ✅ 原生支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 500,000 tokens (500K)
- Max Output Tokens
- 500,000 tokens
- Input Modalities
- Text + Image + PDF
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Cloud API only (Proprietary)
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 2
- Cached Input / 1M
- $ 0.5 -75%
- Output / 1M Tokens
- $ 6
- Tiered Pricing Notes
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 Grok 4.7 Full Benchmark Scorecard
9 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 6 items
CyberGym is a benchmark for evaluating AI agents on cybersecurity tasks, testing their ability to identify vulnerabilities, perform security analysis, and complete security-related challenges in a controlled environment.
DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.
CursorBench 4.0 evaluates coding agents on long-horizon coding tasks from real Cursor sessions. Version 4.0 adds longer-horizon tasks; scores are not comparable with CursorBench 3.2.
SWE-Marathon is an ultra-long-horizon software engineering benchmark covering tasks such as building compilers, optimizing kernels, and developing production-grade services. It measures whether agents can sustain quality across extremely long engineering trajectories.
Terminal-Bench 4.0 evaluates AI agents on real-world work in terminal and command-line containerized environments across 66 tasks, with emphasis on science-adjacent and frontier engineering problems.
FrontierSWE V2 evaluates agents on open-ended technical projects and reports mean@5. Kept separate from FrontierSWE V1 dominance-score results, which are not comparable.
🤖 Agents & Tools 2 items
AA-Briefcase v1.1 evaluates multi-hour professional office work and reports Elo scores. Kept separate from unversioned AA-Briefcase results.
Harvey's Legal Agent Benchmark evaluates AI agents on complex legal workflows and reports the all-pass rate.
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to Grok 4.7
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Grok 4.7 open-source or proprietary?
Grok 4.7 (grok-4.7) is a proprietary commercial model by xAI. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of Grok 4.7?
Grok 4.7 supports 500K input context and 500,000 max output tokens, priced at $2/1M input ($0.5/1M cached) and $6/1M output.