Model
Pixtral Large
Mistral AI
开源 Mistral Research License (MRL) for research; Mistral Commercial License for commercial use
多模态
A 124B parameter multimodal model built on top of Mistral Large 2, featuring frontier-level image understanding capabilities. Excels at understanding documents, charts, and natural images while maintaining strong text-only performance. Features a 123B multimodal decoder and 1B parameter vision encoder with a 128K context window supporting up to 30 high-resolution images.
发布日期2024年11月18日
参数规模124B
上下文长度128K
许可证Mistral Research License (MRL) for research; Mistral Commercial License for commercial use
知识截止—
Benchmarks
评测成绩
| 评测基准 | 类别 | 分数 | 来源 |
|---|---|---|---|
| AI2D | vision reasoning multimodal | 93.8 | 来源 |
| DocVQA | vision multimodal | 93.3 | 来源 |
| ChartQA | reasoning vision multimodal | 88.1 | 来源 |
| VQAv2 | vision multimodal reasoning | 80.9 | 来源 |
| MM-MT-Bench | multimodal communication | 74.0 | 来源 |
| MathVista | math vision multimodal | 69.4 | 来源 |
| MMMU | multimodal reasoning general | 64.0 | 来源 |
Pricing
API 价格对比
| 服务商 | 输入价 | 输出价 | 上下文 | 吞吐(tok/s) | 延迟(s) | 函数调用 | 代码执行 | 联网搜索 |
|---|---|---|---|---|---|---|---|---|
| Mistral | $2.00 | $6.00 | 128K | — | — | ✓ | ✗ | ✗ |
价格单位：美元/百万 token，数据来自社区整理，仅供参考。