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 图像→ 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 84999
vit-base-violence-detection
jaranohaalThis is a Vision Transformer (ViT) model fine-tuned for violence detection. The model is based on google/vit-base-patch16-224-in21k and has been trained on the Real Life Violence Situations dataset from Kaggle to classify images into violent or non-violent categories. The model is intended for use in applications where detecting violent content in images is necessary. This can include: model = ViTForImageClassification.from_pretrained('jaranohaal/vit-base-violence-detection') feature_extractor = ViTFeatureExtractor.from_pretrained('jaranohaal/vit-base-violence-detection')
译文排队中 · 当前显示来源原文
输入 图像→ 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 待核验→ 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 待核验→ 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 ↗Qwen3.8-27B-OBLITERATED
Jaredhollins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 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗kev-0.5b
jaredpalmer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 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗kev-0.6b
jaredpalmer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 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗kev-0.8b
jaredpalmerKev-0.8B is a decision model. It reads one document (the *state*) and a set of typed questions about it, and returns a calibrated probability distribution over the options supplied with each question, in a single forward pass and without generating text. It implements TypeSafe's public System One API (`POST /v1/systemone`), so the TypeSafe SDK works against it unchanged. It is the smallest Kev: a LoRA adapter and a pointer head on Qwen3.5-0.8B-Base that runs on a laptop or a 4 GB GPU. It is intended where memory or cost rules out the larger sizes and the task resembles what it was trained on; out of domain it is markedly less accurate than Kev-4B. This card describes the checkpoint in Kev 1.0, first published on 2026-09-24. **Input.** A state (text, or a JSON object or array rendered as labelled text) and any number of named questions, each of one of three types: Each question is answered as its own row that continues from the shared state, so questions cannot influence one another; the state is computed once and cached.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗kev-27b
jaredpalmer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 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗kev-4b
jaredpalmerKev-4B is a decision model. It reads one document (the *state*) and a set of typed questions about it, and returns a calibrated probability distribution over the options supplied with each question, in a single forward pass and without generating text. It is intended for developers who classify, route, triage or check documents and who need probabilities that can be thresholded, for example to send uncertain cases to human review. It implements TypeSafe's public System One API (`POST /v1/systemone`), so the TypeSafe SDK works against it unchanged. It is a LoRA adapter and a pointer head on Qwen3.5-4B-Base, small enough for one 24 GB GPU or a 32 GB Apple Silicon Mac. This card describes the checkpoint in Kev 1.0, first published on 2026-09-24. **Input.** A state (text, or a JSON object or array rendered as labelled text) and any number of named questions, each of one of three types: Each question is answered as its own row that continues from the shared state, so questions cannot influence one another; the state is computed once and cached.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗kev-9b
jaredpalmerKev-9B is a decision model. It reads one document (the *state*) and a set of typed questions about it, and returns a calibrated probability distribution over the options supplied with each question, in a single forward pass and without generating text. It is intended for developers who classify, route, triage or check documents and who need probabilities that can be thresholded, for example to send uncertain cases to human review. It implements TypeSafe's public System One API (`POST /v1/systemone`), so the TypeSafe SDK works against it unchanged. It is a LoRA adapter and a pointer head on Qwen3.5-9B-Base and fits one 24 GB-class GPU. This card describes version 2, released on 2026-09-30 and included in Kev 1.0. **Input.** A state (text, or a JSON object or array rendered as labelled text) and any number of named questions, each of one of three types: Each question is answered as its own row that continues from the shared state, so questions cannot influence one another; the state is computed once and cached.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
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 文本→ 输出 文本
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 文本 · 图像→ 输出 文本
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 文本→ 输出 文本
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 待核验→ 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 ↗Qwen3.8-27B-Uncensored-GGUF
jaromerUncensored Qwen3.8-27B, published as GGUF quantizations with the multi-token prediction (MTP) head retained and verified. Refusal behaviour has been **substantially reduced**, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. > **MTP tensors verified, not assumed.** Abliteration drops the `mtp.*` tensors: the model > is re-saved through transformers, which does not carry the MTP head, while `config.json` > still advertises it. They are grafted back from the base checkpoint and every file is > inspected after quantization — see Method and Verification.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
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 文本→ 输出 文本
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 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗GLM-5.3-Flash-NestQuant-1.5-4bit
jarrelscy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 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗GLM-5.3-Vision-NestQuant-2-4bit
jarrelscy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 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗aya-23-8B-llamafile
jartineThis repository contains executable weights (which we call llamafiles) that run on Linux, MacOS, Windows, FreeBSD, OpenBSD, and NetBSD for AMD64 and ARM64. Alternatively, you may download an official `llamafile` executable from Mozilla Ocho on GitHub, in which case you can use the Mixtral llamafiles as a simple weights data file. The maximum context size of this model is 8192 tokens. These llamafiles use a default context size of 512 tokens. Whenever you need the maximum context size to be available with llamafile for any given model, you can pass the `-c 0` flag. The temperature on these llamafiles is set to zero by default, because it helps. This can be changed, e.g. `--temp 0.8`.
译文排队中 · 当前显示来源原文
输入 待核验→ 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 ↗WARNING: This README may contain inaccuracies. It was generated automatically by forking TheBloke/dolphin-2.5-mixtral-8x7b-GGUF and piping the README through sed. Errors should be reported to jartine, and do not reflect TheBloke. You can also support his work on Patreon. llamafile is a new format introduced by Mozilla Ocho on Nov 20th 2023. It uses Cosmopolitan Libc to turn LLM weights into runnable llama.cpp binaries that run on the stock installs of six OSes for both ARM64 and AMD64. These Mixtral llamafiles are compatible with llama.cpp from December 13th onwards. Other clients/libraries may not work yet.
译文排队中 · 当前显示来源原文
输入 待核验→ 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 ↗gemma-2-27b-it-llamafile
jartine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 待核验→ 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 ↗gemma-2-9b-it-llamafile
jartine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 待核验→ 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。