Model details

North Small Translate

Cohere · North Small Translate

North Small Translate is a Mixture-of-Experts (MoE) model built specifically for machine translation. The model has a total of 218 billion parameters, with 25 billion activated parameters. The model provides flexible deployment options for research and enterprise applications. Its weights are publicly available in W4A16, FP8, and BF16 formats under the Creative Commons Attribution-NonCommercial 4.0 license, for non-commercial use only.

能读 33K
Official price¥0/ ¥0每百万 Token
2家在卖

The best way to buy North Small Translate

The best deal for each of three ways to buy. Tap a card to see every option of that kind.

Pay-as-you-go API · relay stationsFor coding and tools like Cursor and Claude Code
For using the web app and mobile app, no coding
Official subscriptionsFor a genuine official plan in your own name

North Small Translate

North Small Translate is a Mixture-of-Experts (MoE) model built specifically for machine translation. The model has a total of 218 billion parameters, with 25 billion activated parameters. The model provides flexible deployment options for research and enterprise applications. Its weights are publicly available in W4A16, FP8, and BF16 formats under the Creative Commons Attribution-NonCommercial 4.0 license, for non-commercial use only.

View intro source
Official price · Input¥0.0000
Official price · Output¥0.0000
Sellers2 家

The best way to buy North Small Translate

The best deal for each of three ways to buy. Tap a card to see every option of that kind.

Pay-as-you-go API · relay stationsFor coding and tools like Cursor and Claude Code
For using the web app and mobile app, no coding
Official subscriptionsFor a genuine official plan in your own name
No reviews yet — write the first oneSee reviews ↓

模型介绍

North Small Translate is a Mixture-of-Experts (MoE) model built specifically for machine translation. The model has a total of 218 billion parameters, with 25 billion activated parameters. The model provides flexible deployment options for research and enterprise applications. Its weights are publicly available in W4A16, FP8, and BF16 formats under the Creative Commons Attribution-NonCommercial 4.0 license, for non-commercial use only.

模型基础信息

厂商
Cohere
模型类型
文本与多模态
一次能读多少
33K Token一次对话能塞进去的最大内容量,长文档、长代码要看这项
一次能写多少
16,000 Token单次回答的长度上限
能接收什么
文本可以发给它的内容类型
能产出什么
文本它能生成的内容类型
怎么计费
按 Token 计费官方按什么单位收钱
现在还能用吗
可以用 · 状态来源
这些资料是哪个地区的资料适用地区
全球按厂商全球公布的资料显示;国内没单独公布时,也用这一份。
它会做什么回答风格可调会写字

官方价格

折扣与价格评分按全球的官方价计算

计价项适用范围官方价格
输入全球0 CNY每百万 Token
输出全球0 CNY每百万 Token
它还叫这些名字(2 条)
North-Small-Translatenorth-small-translate-09-2026

不同地方写法可能不一样,列在这里方便你对上号。名字太模糊、认不准的不会公开。

User reviews

No reviews yet. If you have used it, share the first honest review and help others avoid pitfalls.

Review this model

Rating
Optional
编辑器加载中…