Grok 4 Reasoning: pricing, context window and benchmarks
Grok 4 Reasoning is a frontier model from xAI. It offers a 2,000,000-token context window, costs $19.67 per million input tokens and $93.29 per million output tokens, and averages 87.8 across the index's benchmark suite.
Pricing
Grok 4 Reasoning costs $19.67 per million input tokens and $93.29 per million output tokens. A blended 3:1 input-to-output mix works out to about $38.08 per million tokens. Cached input is listed at $2.46 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $19.67 | per 1M tokens |
| Output | $93.29 | per 1M tokens |
| Cached input | $2.46 | per 1M tokens |
| Blended 3:1 | $38.08 | estimate per 1M tokens |
| 1M in + 1M out | $112.96 | 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 | 88.5 | 12 | 98th | |
| GPQA Diamond | 81.9 | 31 | 95th | |
| SWE-bench Verified | 78.0 | 16 | 97th | |
| HumanEval | 93.8 | 4 | 99th | |
| MATH-500 | 94.4 | 6 | 99th | |
| AIME 2025 | 85.6 | 30 | 95th | |
| LiveCodeBench | 85.1 | 2 | 100th | |
| IFEval | 93.4 | 19 | 97th | |
| TruthfulQA | 89.4 | 7 | 99th | |
| HellaSwag | 95.2 | 6 | 99th | |
| MMMU | 80.8 | 47 | 92th | |
| Arena Elo | 1487.6 | 10 | 98th |
What Grok 4 Reasoning is good for
Grok 4 Reasoning 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 $19.67 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 (87.8), placing it #11 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 $19.67 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 Max | OpenAI | 2000000 | $20.50 | 87.9 |
| Claude Opus 4.5 Max | Anthropic | 1000000 | $20.90 | 87.8 |
| GPT-5.1 Pro | OpenAI | 200000 | $19.77 | 87.8 |
| Grok 4 Reasoning | xAI | 2000000 | $19.67 | 87.8 |
| Claude Opus 4.5 | Anthropic | 400000 | $19.42 | 87.7 |
| Claude Sonnet 4.5 Reasoning | Anthropic | 400000 | $19.48 | 87.7 |
FAQ
How much does Grok 4 Reasoning cost?
Grok 4 Reasoning is listed at $19.67 per million input tokens and $93.29 per million output tokens. Cached input is $2.46 per million tokens. A blended 3:1 input-to-output mix is about $38.08 per million tokens.
What is the context window of Grok 4 Reasoning?
Grok 4 Reasoning has a context window of 2,000,000 tokens and can emit up to 65,536 output tokens per request in this index.
Is Grok 4 Reasoning open weights?
No. Grok 4 Reasoning is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Grok 4 Reasoning score on benchmarks?
Grok 4 Reasoning averages 87.8 across the scored benchmarks in this index, ranking #11 of 600 models. Its strongest relative result is LiveCodeBench at 85.1.
What is Grok 4 Reasoning best for?
Grok 4 Reasoning 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 $19.67 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.