Grok 4 Mini: pricing, context window and benchmarks
Grok 4 Mini is a multimodal model from xAI. It offers a 65,536-token context window, costs $12.21 per million input tokens and $65.41 per million output tokens, and averages 77.9 across the index's benchmark suite.
Pricing
Grok 4 Mini costs $12.21 per million input tokens and $65.41 per million output tokens. A blended 3:1 input-to-output mix works out to about $25.51 per million tokens. Cached input is listed at $1.45 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $12.21 | per 1M tokens |
| Output | $65.41 | per 1M tokens |
| Cached input | $1.45 | per 1M tokens |
| Blended 3:1 | $25.51 | estimate per 1M tokens |
| 1M in + 1M out | $77.62 | 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 | 79.5 | 195 | 68th | |
| GPQA Diamond | 75.4 | 134 | 78th | |
| SWE-bench Verified | 69.3 | 124 | 79th | |
| HumanEval | 83.5 | 144 | 76th | |
| MATH-500 | 79.4 | 224 | 63th | |
| AIME 2025 | 73.5 | 197 | 67th | |
| LiveCodeBench | 71.6 | 158 | 74th | |
| IFEval | 84.4 | 203 | 66th | |
| TruthfulQA | 79.1 | 211 | 65th | |
| HellaSwag | 87.1 | 172 | 71th | |
| MMMU | 74.6 | 168 | 72th | |
| Arena Elo | 1423.4 | 132 | 78th |
What Grok 4 Mini is good for
Grok 4 Mini 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 $12.21 per million input tokens, it sits in the mid-range of the index, and the 65,536-token context window is enough for large files and multi-file diffs.
Strengths
- Accepts more than text, including image input where the provider supports it.
- 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 $12.21 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| ERNIE 4.0 Turbo | Baidu | 65536 | $12.00 | 78.0 |
| Llama 4 Scout Chat | Meta AI | 32768 | $4.66 | 78.0 |
| Grok 4 Mini | xAI | 65536 | $12.21 | 77.9 |
| ERNIE 4.0 Reasoning | Baidu | 65536 | $12.20 | 77.8 |
| MiniMax-Text Chat | MiniMax | 128000 | $4.26 | 77.8 |
| Sonar Max | Perplexity | 32768 | $11.60 | 77.8 |
FAQ
How much does Grok 4 Mini cost?
Grok 4 Mini is listed at $12.21 per million input tokens and $65.41 per million output tokens. Cached input is $1.45 per million tokens. A blended 3:1 input-to-output mix is about $25.51 per million tokens.
What is the context window of Grok 4 Mini?
Grok 4 Mini has a context window of 65,536 tokens and can emit up to 65,536 output tokens per request in this index.
Is Grok 4 Mini open weights?
No. Grok 4 Mini is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Grok 4 Mini score on benchmarks?
Grok 4 Mini averages 77.9 across the scored benchmarks in this index, ranking #175 of 600 models. Its strongest relative result is Arena Elo at 1423.4.
What is Grok 4 Mini best for?
Grok 4 Mini 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 $12.21 per million input tokens, it sits in the mid-range of the index, and the 65,536-token context window is enough for large files and multi-file diffs.