vllmsafetensorsmistralmistral-commonenfrdeesptitjakoruzharfaidmsneplrosrsvtrukvihibnarxiv:2506.10910base_model:mistralai/Mistral-Small-3.1-24B-Instruct-2503base_model:finetune:mistralai/Mistral-Small-3.1-24B-Instruct-2503license:apache-2.0region:us
上下文
32,768 tokens
最大输出
8,192 tokens
发布时间
2025/6/4
供应商
1
Overview
Magistral-Small-2506 is a large language model developed by Mistral. It supports 32,768 tokens context and is available through 1 API provider(s).
Key Highlights
- Unknown / Not disclosed
Brand
Mistral
Organization
国家: France
View all models, pricing and details from Mistral.
Specifications
Basic Information
| 模型 | Magistral-Small-2506 |
| 品牌 | Mistral |
| Version | 2506 |
| Model Type | vllm |
| 状态 | stable |
| 发布时间 | 2025/6/4 |
| 热度 | 103274 |
Architecture
| Parameter Size | 23.6B |
| Architecture Type | mistral |
| Attention Mechanism | causal-mha-gqa |
| Tokenizer | Unknown / Not disclosed |
| Vocabulary Size | Unknown / Not disclosed |
Context & I/O
| 上下文 | 32,768 tokens |
| 最大输出 | 8,192 tokens |
| Modalities | Unknown / Not disclosed |
| Languages | en,fr,de,es,pt,it,ja,ko,ru,zh,ar,fa,id,ms,ne,pl,ro,sr,sv,tr,uk,vi,hi,bn |
Capabilities
| Vision | No |
| Audio | No |
| Reasoning | No |
| Function Call | No |
| MCP | No |
| JSON Mode | No |
| Embedding | No |
Training Data
| Training Dataset | Unknown / Not disclosed |
| Estimated Data Size | Unknown / Not disclosed |
| Knowledge Cutoff | Unknown / Not disclosed |
Inference & Deployment
| API Access | Yes |
| VRAM Estimate | Unknown / Not disclosed |
| Quantization Support | Unknown / Not disclosed |
| Hardware Requirements | Unknown / Not disclosed |
Safety & Compliance
| Safety Evaluations | Unknown / Not disclosed |
| Content Policy | Unknown / Not disclosed |
| Region Restrictions | Unknown / Not disclosed |
License & Pricing
| License | apache-2.0 |
| Commercial Use | Unknown / Not disclosed |
| Open Source | Yes |
Provider & Pricing
价格变动
暂无价格变动。
基准测试
No benchmark data available.
Changelog
- Page created / data imported2026/9/23
- Last updated2026/9/23
FAQ
What is Magistral-Small-2506?
Magistral-Small-2506 is a large language model developed by Mistral.
Who developed Magistral-Small-2506?
Magistral-Small-2506 was developed by Mistral. You can learn more on the brand page or official website.
What is the context length of Magistral-Small-2506?
Magistral-Small-2506 supports up to 32,768 tokens of context.
How much does Magistral-Small-2506 API cost?
API pricing for Magistral-Small-2506 starts at ¥0.000/1M per 1M input tokens and ¥0.000/1M per 1M output tokens. See the pricing table above for provider-specific rates.