Grok 4.6 Official Specifications, Pricing & Benchmarks
xAI flagship reasoning model with 500K context/output limit and aggressive $6/1M output pricing.
📋 Grok 4.6 Official API & System Card Specifications
Verified against official xAI developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- grok-4.6
- Release Date
- 2026-08-12
- 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
- ≤200K ($2/$6); >200K ($4/$12); supports up to 500K max output tokens
🏆 Official Benchmark Results
Sourced from official System Card / Model Card & technical reports
PhD-level Google-proof science reasoning questions
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks.
LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code.
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 Grok 4.6 Full Benchmark Scorecard
8 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 4 items
DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.
FrontierCode is Cognition's coding evaluation that tests whether models can pass difficult coding tasks while meeting the standards of high-quality production codebases. The Diamond subset contains the hardest problems.
Terminal-Bench 3.0 is a release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal on real-world, end-to-end tasks.
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.
🤖 Agents & Tools 3 items
GDPval-AA evaluates AI agents on economically valuable professional knowledge-work tasks and reports performance as an Elo score.
APEX-Agents is a benchmark evaluating AI agents on long horizon professional tasks that require sustained reasoning, planning, and execution across complex multi-step workflows.
AA-Briefcase is an Artificial Analysis evaluation of AI systems on professional knowledge-work tasks, reported as an Elo score.
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to Grok 4.6
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Grok 4.6 open-source or proprietary?
Grok 4.6 (grok-4.6) 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 4.6?
Grok 4.6 supports 500K input context and 500,000 max output tokens, priced at $2/1M input ($0.5/1M cached) and $6/1M output.