This model was introduced in the paper **LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression** (Pan et al, 2024). It is a BERT multilingual base model (cased) finetuned to perform token classification for task agnostic prompt compression. The probability `$p_{preserve}$` of each token `$x_i$` is used as the metric for compression. This model is trained on the extractive text compression dataset constructed with the methodology proposed in the **LLMLingua-2**, using training examples from MeetingBank (Hu et al, 2023) as the seed data. You can evaluate the model on downstream tasks such as question answering (QA) and summarization over compressed meeting transcripts using this dataset. For more details, please check the project page of LLMLingua-2 and LLMLingua Series.
Explore AI models 85003
This model was introduced in the paper **LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression** (Pan et al, 2024). It is a XLM-RoBERTa (large-sized model) finetuned to perform token classification for task agnostic prompt compression. The probability $p_{preserve}$ of each token $x_i$ is used as the metric for compression. This model is trained on the extractive text compression dataset constructed with the methodology proposed in the **LLMLingua-2**, using training examples from MeetingBank (Hu et al, 2023) as the seed data. You can evaluate the model on downstream tasks such as question answering (QA) and summarization over compressed meeting transcripts using this dataset. For more details, please check the home page of LLMLingua-2 and LLMLingua Series.
longcoder-base
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Mage-ViT
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Mage-VL
Microsoft**Mage-VL** is a **codec-native, proactive-streaming multimodal foundation model** for image and video understanding, whose visual encoder is trained **entirely from scratch** at a compact **4B** scale. It targets a modern *Moravec's paradox* of VLMs — strong at complex offline reasoning, yet slow and compute-heavy on simple real-time streaming perception. Instead of decoding video into uniformly-sampled frames and pushing a dense grid of patch tokens through a frozen web-pretrained ViT, Mage-VL follows the structure of modern video codecs: it separates a stream into **anchor (I) frames** and **predicted (P) frames**, keeps every anchor patch, and retains only the predicted-frame patches where the codec spends bits — the regions carrying real motion and new detail. This codec-aligned sparsity cuts visual tokens by **over 75%** while preserving spatio-temporal context, yielding **up to 3.5× wall-clock inference speedup** over uniform frame sampling. On top of this pair, a **System 1 & System 2 dual-process design** adds proactive streaming inside a single model: a lightweight **cognition gate** (System 1) watches each rolling codec window and stays silent on routine content, invoking the full VLM (System 2) only when a response-worthy event completes — no multi-agent pipeline required. A **single checkpoint**, `microsoft/Mage-VL`, is one unified model that **simultaneously** provides image & video understanding **and** the proactive streaming gate — the same weights answer offline image/video questions and drive event-gated commentary. It covers every Mage-VL capability: image understanding, frame-sampled video, traditional H.264/HEVC codec video, neural DCVC-RT codec video, and event-gated streaming. The repository bundles the codec processor, the neural codec package, and the proactive gate weights — no separate understanding, NVC, or streaming checkpoint is required.
MagenticBrain
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Magma-8B
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
MAI-DS-R1
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
MAI-DS-R1-FP8
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
maira-2
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
maira-2-sae
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
markuplm-base
MicrosoftMarkupLM is a simple but effective multi-modal pre-training method of text and markup language for visually-rich document understanding and information extraction tasks, such as webpage QA and webpage information extraction. MarkupLM archives the SOTA results on multiple datasets. For more details, please refer to our paper: MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding Junlong Li, Yiheng Xu, Lei Cui, Furu Wei, ACL 2022
markuplm-base-finetuned-websrc
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
markuplm-large
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
markuplm-large-finetuned-websrc
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
mattergen
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
mdeberta-v3-base
MicrosoftDeBERTa improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. With those two improvements, DeBERTa out perform RoBERTa on a majority of NLU tasks with 80GB training data. In DeBERTa V3, we further improved the efficiency of DeBERTa using ELECTRA-Style pre-training with Gradient Disentangled Embedding Sharing. Compared to DeBERTa, our V3 version significantly improves the model performance on downstream tasks. You can find more technique details about the new model from our paper. mDeBERTa is multilingual version of DeBERTa which use the same structure as DeBERTa and was trained with CC100 multilingual data. The mDeBERTa V3 base model comes with 12 layers and a hidden size of 768. It has 86M backbone parameters with a vocabulary containing 250K tokens which introduces 190M parameters in the Embedding layer. This model was trained using the 2.5T CC100 data as XLM-R.
MediPhi
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
MediPhi-Clinical
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
MediPhi-Guidelines
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
MediPhi-Instruct
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
MediPhi-MedCode
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
MediPhi-MedWiki
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
MediPhi-PubMed
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
No matching models
Adjust provider, category or input/output filters. New models are added continuously.
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
Understand before you choose
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.