Grok 3: pricing, context window and benchmarks
Grok 3 is a multimodal model from xAI. It offers a 128,000-token context window, costs $15.84 per million input tokens and $70.31 per million output tokens, and averages 82.8 across the index's benchmark suite.
Pricing
Grok 3 costs $15.84 per million input tokens and $70.31 per million output tokens. A blended 3:1 input-to-output mix works out to about $29.46 per million tokens. Cached input is listed at $2.12 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $15.84 | per 1M tokens |
| Output | $70.31 | per 1M tokens |
| Cached input | $2.12 | per 1M tokens |
| Blended 3:1 | $29.46 | estimate per 1M tokens |
| 1M in + 1M out | $86.15 | 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 | 81.9 | 122 | 80th | |
| GPQA Diamond | 80.0 | 57 | 91th | |
| SWE-bench Verified | 72.6 | 65 | 89th | |
| HumanEval | 85.3 | 109 | 82th | |
| MATH-500 | 88.7 | 63 | 90th | |
| AIME 2025 | 81.1 | 73 | 88th | |
| LiveCodeBench | 74.3 | 103 | 83th | |
| IFEval | 91.0 | 55 | 91th | |
| TruthfulQA | 85.4 | 62 | 90th | |
| HellaSwag | 91.4 | 50 | 92th | |
| MMMU | 79.1 | 71 | 88th | |
| Arena Elo | 1447.2 | 83 | 86th |
What Grok 3 is good for
Grok 3 is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $15.84 per million input tokens, it sits in the mid-range of the index, and the 128,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 128,000-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 $15.84 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| DeepSeek-R1 Instruct | DeepSeek | 1000000 | $5.90 | 83.1 |
| Kimi K2 | Moonshot AI | 128000 | $5.85 | 83.0 |
| GPT-4.1 Turbo | OpenAI | 1000000 | $16.12 | 82.9 |
| Grok 3 Reasoning | xAI | 200000 | $16.07 | 82.9 |
| DeepSeek-R1 | DeepSeek | 128000 | $5.83 | 82.8 |
| Grok 3 | xAI | 128000 | $15.84 | 82.8 |
FAQ
How much does Grok 3 cost?
Grok 3 is listed at $15.84 per million input tokens and $70.31 per million output tokens. Cached input is $2.12 per million tokens. A blended 3:1 input-to-output mix is about $29.46 per million tokens.
What is the context window of Grok 3?
Grok 3 has a context window of 128,000 tokens and can emit up to 4,096 output tokens per request in this index.
Is Grok 3 open weights?
No. Grok 3 is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Grok 3 score on benchmarks?
Grok 3 averages 82.8 across the scored benchmarks in this index, ranking #78 of 600 models. Its strongest relative result is Arena Elo at 1447.2.
What is Grok 3 best for?
Grok 3 is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $15.84 per million input tokens, it sits in the mid-range of the index, and the 128,000-token context window is enough for large files and multi-file diffs.