Grok 3 Max: pricing, context window and benchmarks
Grok 3 Max is a frontier model from xAI. It offers a 2,000,000-token context window, costs $17.66 per million input tokens and $89.12 per million output tokens, and averages 85.9 across the index's benchmark suite.
Pricing
Grok 3 Max costs $17.66 per million input tokens and $89.12 per million output tokens. A blended 3:1 input-to-output mix works out to about $35.53 per million tokens. Cached input is listed at $1.59 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $17.66 | per 1M tokens |
| Output | $89.12 | per 1M tokens |
| Cached input | $1.59 | per 1M tokens |
| Blended 3:1 | $35.53 | estimate per 1M tokens |
| 1M in + 1M out | $106.78 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 87.3 | 30 | 95th | |
| GPQA Diamond | 80.9 | 46 | 92th | |
| SWE-bench Verified | 73.6 | 60 | 90th | |
| HumanEval | 91.9 | 25 | 96th | |
| MATH-500 | 91.9 | 23 | 96th | |
| AIME 2025 | 86.6 | 23 | 96th | |
| LiveCodeBench | 79.7 | 47 | 92th | |
| IFEval | 92.6 | 27 | 96th | |
| TruthfulQA | 86.7 | 42 | 93th | |
| HellaSwag | 91.8 | 43 | 93th | |
| MMMU | 82.3 | 28 | 95th | |
| Arena Elo | 1475.8 | 25 | 96th |
What Grok 3 Max is good for
Grok 3 Max sits in the frontier tier of the index. It is aimed at work where answer quality matters more than unit cost: hard reasoning, multi-step coding, document analysis and multimodal inputs. At $17.66 per million input tokens and a 2,000,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.
Strengths
- Top-tier average benchmark score (85.9), placing it #36 of 600.
- Large 2,000,000-token context window for long documents and agent traces.
- Accepts more than text, including image input where the provider supports it.
- Reasoning-oriented profile, useful for multi-step problems and structured analysis.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Premium input pricing at $17.66 per million tokens.
- Cost can climb quickly on long outputs and high-volume traffic.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| GPT-5.1 | OpenAI | 2000000 | $19.01 | 86.0 |
| Claude Opus 4.5 Vision | Anthropic | 200000 | $17.70 | 85.9 |
| Claude Sonnet 4.5 Turbo | Anthropic | 1000000 | $18.37 | 85.9 |
| Grok 3 Max | xAI | 2000000 | $17.66 | 85.9 |
| Qwen3-Max Max | Alibaba Cloud | 400000 | $18.53 | 85.9 |
| Qwen3-Max Reasoning | Alibaba Cloud | 2000000 | $18.12 | 85.9 |
FAQ
How much does Grok 3 Max cost?
Grok 3 Max is listed at $17.66 per million input tokens and $89.12 per million output tokens. Cached input is $1.59 per million tokens. A blended 3:1 input-to-output mix is about $35.53 per million tokens.
What is the context window of Grok 3 Max?
Grok 3 Max has a context window of 2,000,000 tokens and can emit up to 32,768 output tokens per request in this index.
Is Grok 3 Max open weights?
No. Grok 3 Max is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Grok 3 Max score on benchmarks?
Grok 3 Max averages 85.9 across the scored benchmarks in this index, ranking #36 of 600 models. Its strongest relative result is Arena Elo at 1475.8.
What is Grok 3 Max best for?
Grok 3 Max sits in the frontier tier of the index. It is aimed at work where answer quality matters more than unit cost: hard reasoning, multi-step coding, document analysis and multimodal inputs. At $17.66 per million input tokens and a 2,000,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.