mj_shortenCompare mj_shorten API pricing, supported endpoints, capabilities and access options on Modelsell.
BPE (vendor-specific)Scores on standardized evaluations. Higher percentages are better — and rank percentile shows
Metrics sourced fromArtificial Analysis 2026-09-30·Mj Shorten
This model is not included in the current benchmark snapshot.
Missing models or measurements are not zero scores.
Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.
一段提示词不断追加形容词、风格词和补充说明后,常会变得难以修改。Shorten 接收这段长描述,给出更简洁的表达建议,适合整理旧提示词、检查重复内容,或为同一个画面准备几种更清楚的写法。它返回的是文本建议,图片仍需通过 Imagine 等生成操作制作。
精简时最值得关注的是画面的核心:主体是什么、正在做什么、处于怎样的环境,以及需要保留的光线和构图。以产品图为例,“白色陶瓷杯、窗边侧光、浅灰背景、右侧留白”通常比一连串含义接近的品质形容词更便于检查和调整。
不一定。杯柄朝向、人物位置、物体数量等具体要求,即使只占几个字,也可能决定图片能否使用。把精简结果当作候选版本,先确认必要条件没有被删去,再实际生成比较;不要只按字数选择。
提交需要整理的原始绘图描述即可,无须提供已完成的图片任务。若提示中带有画幅比例等生成参数,应另行保存,并在后续生成时检查是否正确带回。
把完整的长提示词提交给 Shorten,例如:“一只白色陶瓷咖啡杯摆在窗边的浅灰色桌面上,清晨柔和的自然侧光,简洁干净的背景,安静温暖的氛围,杯子在左侧,右边保留大片空白用于排版。”
收到建议后,重点检查“白色陶瓷杯、侧光、主体在左、右侧留白”是否仍在。选择一份表达清楚的版本用于生成,并保留原稿作对照。若短版丢失排版要求,手动补回后再试;Shorten 的建议不能代替对最终画面的检查。
Use the linked documentation for model-specific request parameters and examples.
All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.
Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.
| Supplier | RPM | TPM | RPD |
|---|---|---|---|
| 标准按次 | Unlimited | Unlimited | Unlimited |
No restriction
Compare mj_shorten API pricing, supported endpoints, capabilities and access options on Modelsell.
Create an API key with access to mj_shorten, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.
Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.
Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.
