xclip-base-patch16-ucf-4-shot
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。
基础资料已收录 · 缺失资料后续补充
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DISCOVER & COMPARE
探索 AI 模型 68
xclip-base-patch16-ucf-8-shot
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。
基础资料已收录 · 缺失资料后续补充
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗xclip-base-patch16-zero-shot
MicrosoftX-CLIP model (base-sized, patch resolution of 16) trained on Kinetics-400. It was introduced in the paper Expanding Language-Image Pretrained Models for General Video Recognition by Ni et al. and first released in this repository. Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team. X-CLIP is a minimal extension of CLIP for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs.
译文排队中 · 当前显示来源原文
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗xclip-base-patch32
MicrosoftX-CLIP model (base-sized, patch resolution of 32) trained fully-supervised on Kinetics-400. It was introduced in the paper Expanding Language-Image Pretrained Models for General Video Recognition by Ni et al. and first released in this repository. Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team. X-CLIP is a minimal extension of CLIP for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs.
译文排队中 · 当前显示来源原文
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗xclip-base-patch32-16-frames
MicrosoftX-CLIP model (base-sized, patch resolution of 32) trained fully-supervised on Kinetics-400. It was introduced in the paper Expanding Language-Image Pretrained Models for General Video Recognition by Ni et al. and first released in this repository. Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team. X-CLIP is a minimal extension of CLIP for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs.
译文排队中 · 当前显示来源原文
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗xclip-large-patch14
MicrosoftX-CLIP model (large-sized, patch resolution of 14) trained fully-supervised on Kinetics-400. It was introduced in the paper Expanding Language-Image Pretrained Models for General Video Recognition by Ni et al. and first released in this repository. Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team. X-CLIP is a minimal extension of CLIP for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs.
译文排队中 · 当前显示来源原文
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗xclip-large-patch14-16-frames
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。
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗xclip-large-patch14-kinetics-600
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。
基础资料已收录 · 缺失资料后续补充
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
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。
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗InternVideo1.0
OpenGVLab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。
基础资料已收录 · 缺失资料后续补充
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗InternVideo2-Stage1-1B-224p-K400
OpenGVLab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。
基础资料已收录 · 缺失资料后续补充
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗InternVideo2-Stage2_6B
OpenGVLab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。
基础资料已收录 · 缺失资料后续补充
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗UMT
OpenGVLab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。
基础资料已收录 · 缺失资料后续补充
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VideoMAEv2-Base
OpenGVLabVideoMAEv2-Base model pre-trained for 800 epochs in a self-supervised way on UnlabeldHybrid-1M dataset. It was introduced in the paper [[CVPR23]VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://arxiv.org/abs/2203.12602) by Wang et al. and first released in GitHub.
译文排队中 · 当前显示来源原文
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VideoMAEv2-giant
OpenGVLab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。
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VideoMAEv2-Huge
OpenGVLabVideoMAEv2-Huge model pre-trained for 1200 epochs in a self-supervised way on UnlabeldHybrid-1M dataset. It was introduced in the paper [[CVPR23]VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://arxiv.org/abs/2203.12602) by Wang et al. and first released in GitHub.
译文排队中 · 当前显示来源原文
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VideoMAEv2-Large
OpenGVLabVideoMAEv2-Large model pre-trained for 800 epochs in a self-supervised way on UnlabeldHybrid-1M dataset. It was introduced in the paper [[CVPR23]VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://arxiv.org/abs/2203.12602) by Wang et al. and first released in GitHub.
译文排队中 · 当前显示来源原文
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VideoMamba
OpenGVLab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。
基础资料已收录 · 缺失资料后续补充
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗vjepa2-vitl-fpc16-256-ssv2
qubvel-hfA frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of VJEPA, resulting in state-of-the-art video understanding capabilities, leveraging data and model sizes at scale. The code is released in this repository. 💡 This is V-JEPA 2 model with video classification head pretrained on Something-Something-V2 dataset.
译文排队中 · 当前显示来源原文
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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。
基础资料已收录 · 缺失资料后续补充
输入 视频→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
仅比较同一渠道的基础文本 Token 报价
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
MODEL HANDBOOK
读懂模型，再做选择
API 价格应该怎么比较？+
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
开放权重，就代表可以免费商用吗？+
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
排行榜第一，就是最适合我的模型吗？+
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。