Grok 4 Pro: pricing, context window and benchmarks
Grok 4 Pro is a frontier model from xAI. It offers a 1,000,000-token context window, costs $19.00 per million input tokens and $77.72 per million output tokens, and averages 85.4 across the index's benchmark suite.
Pricing
Grok 4 Pro costs $19.00 per million input tokens and $77.72 per million output tokens. A blended 3:1 input-to-output mix works out to about $33.68 per million tokens. Cached input is listed at $1.64 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $19.00 | per 1M tokens |
| Output | $77.72 | per 1M tokens |
| Cached input | $1.64 | per 1M tokens |
| Blended 3:1 | $33.68 | estimate per 1M tokens |
| 1M in + 1M out | $96.72 | 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 | 84.9 | 64 | 89th | |
| GPQA Diamond | 79.2 | 69 | 89th | |
| SWE-bench Verified | 74.7 | 46 | 92th | |
| HumanEval | 89.7 | 54 | 91th | |
| MATH-500 | 92.3 | 18 | 97th | |
| AIME 2025 | 85.4 | 34 | 94th | |
| LiveCodeBench | 77.8 | 68 | 89th | |
| IFEval | 91.3 | 49 | 92th | |
| TruthfulQA | 86.0 | 52 | 91th | |
| HellaSwag | 92.8 | 27 | 96th | |
| MMMU | 84.9 | 6 | 99th | |
| Arena Elo | 1487.5 | 11 | 98th |
What Grok 4 Pro is good for
Grok 4 Pro 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 $19.00 per million input tokens and a 1,000,000-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 (85.4), placing it #42 of 600.
- Large 1,000,000-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 $19.00 per million tokens.
- Cost can climb quickly on long outputs and high-volume traffic.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Claude Opus 4.5 Turbo | Anthropic | 2000000 | $19.57 | 85.7 |
| Gemini 3 Pro Vision | Google DeepMind | 200000 | $17.59 | 85.5 |
| Grok 4 Pro | xAI | 1000000 | $19.00 | 85.4 |
| o4 | OpenAI | 2000000 | $17.74 | 85.4 |
| o3 Reasoning | OpenAI | 200000 | $18.07 | 85.3 |
| GPT-4.1 Pro | OpenAI | 400000 | $17.56 | 85.2 |
FAQ
How much does Grok 4 Pro cost?
Grok 4 Pro is listed at $19.00 per million input tokens and $77.72 per million output tokens. Cached input is $1.64 per million tokens. A blended 3:1 input-to-output mix is about $33.68 per million tokens.
What is the context window of Grok 4 Pro?
Grok 4 Pro has a context window of 1,000,000 tokens and can emit up to 128,000 output tokens per request in this index.
Is Grok 4 Pro open weights?
No. Grok 4 Pro is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Grok 4 Pro score on benchmarks?
Grok 4 Pro averages 85.4 across the scored benchmarks in this index, ranking #42 of 600 models. Its strongest relative result is Arena Elo at 1487.5.
What is Grok 4 Pro best for?
Grok 4 Pro 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 $19.00 per million input tokens and a 1,000,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.