多模态模型企业部署Agent多语言
Command A+
分类：多模态模型 / 上下文：256K / 调用名：command-a-plus-05-2026
Command A+ 是 Cohere 于 2026 年 5 月发布的开源企业模型，面向复杂推理、多模态和多语言 Agent 任务。
推理视觉函数调用tool_use长上下文multilingual开放权重结构化输出
官方核验于 2026-08-22
Cohere
Cohere 以检索、重排、嵌入和企业文本工作流见长；当前官网还将 North Mini Code 明确定位为 Agentic coding model，形成从企业搜索到代码 Agent 的产品组合。
官方入口原生官方接口付费入口语言模型
主分类：语言模型
适合：知识库检索 / 重排嵌入 / 企业搜索
付费：信用卡 / 企业合同
地区：国际可用
接入判断
按原生接口接Cohere 适合作为官方原生入口，接入前先按文档核对鉴权方式、模型 ID 和计费口径。
协议：官方原生 API
价格：以官方价格页为准
模型：已收录 36 个
模型能力
语言模型代码开发Agent终端任务
North Mini Code
分类：语言模型 / 上下文：256K / 调用名：North-Mini-Code-1.0
North Mini Code 是 Cohere 于 2026 年 6 月发布的 30B/3B 激活开放模型，面向 Agent 编程、代码生成和终端任务。
代码推理tool_use开放权重长上下文函数调用结构化输出
语言模型Agent知识库检索长文问答
Command A
分类：语言模型 / 上下文：256K / 调用名：command-a-03-2025
Command A is a performant mode good at tool use, RAG, agents, and multilingual use cases. It has 111 billion parameters and a 256k context length.
函数调用长上下文
语言模型Agent知识库检索长文问答
Command R7B
分类：语言模型 / 上下文：128K / 调用名：command-r7b-12-2024
Command R7B is the smallest, fastest, and final model in our R family of enterprise-focused large language models. It excels at RAG, tool use, and agents.
函数调用长上下文
语言模型机器翻译多语言应用跨语种工作流
Command A Translate
分类：语言模型 / 上下文：8K / 调用名：command-a-translate-08-2025
Command A Translate is a state of the art model performant in 23 languages. It has a context length of 16K tokens and 111B parameters.
能力标签未整理
语言模型复杂推理多步任务Agent
Command A Reasoning
分类：语言模型 / 上下文：256K / 调用名：command-a-reasoning-08-2025
Command A Reasoning excels in tool use, agentic workflows, and complex problem-solving. It has 111 billion parameters and a 256k context length.
推理函数调用长上下文
多模态模型视觉理解图文问答多语言任务
Command A Vision
分类：多模态模型 / 上下文：128K / 调用名：command-a-vision-07-2025
Command A Vision is a powerful visual language model capable of interacting with image inputs. This document contains information about its capabilities.
视觉长上下文
语言模型Agent知识库检索长文问答
Command R 08-2024
分类：语言模型 / 上下文：128K / 调用名：command-r-08-2024
Command R is a conversational model that excels in language tasks and supports multiple languages, making it ideal for coding use cases.
长上下文
语言模型Agent知识库检索长文问答
Command R+ 08-2024
分类：语言模型 / 上下文：128K / 调用名：command-r-plus-08-2024
Command R+ is Cohere's optimized for conversational interaction and long-context tasks, best suited for complex RAG workflows and multi-step tool use.
函数调用长上下文
语言模型Agent知识库检索长文问答
Command R 03-2024
分类：语言模型 / 上下文：0.128K / 调用名：command-r-03-2024
Command R is an instruction-following conversational model that performs language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents.
函数调用
语言模型Agent知识库检索长文问答
Command R+ 04-2024
分类：语言模型 / 上下文：0.128K / 调用名：command-r-plus-04-2024
Command R+ is an instruction-following conversational model that performs language tasks at a higher quality, more reliably, and with a longer context than previous models. It is best suited for complex RAG workflows and multi-step tool use.
函数调用
语言模型Agent知识库检索长文问答
Command R+
分类：语言模型 / 上下文：128K / 调用名：command-r-plus
Command R+ is Cohere's optimized for conversational interaction and long-context tasks, best suited for complex RAG workflows and multi-step tool use.
函数调用长上下文
语言模型Agent知识库检索长文问答
Command R
分类：语言模型 / 上下文：128K / 调用名：command-r
Command R is a conversational model that excels in language tasks and supports multiple languages, making it ideal for coding use cases.
长上下文
语言模型Agent知识库检索长文问答
Command Light
分类：语言模型 / 上下文：0.004K / 调用名：command-light
A smaller, faster version of command . Almost as capable, but a lot faster.
能力标签未整理
语言模型Agent知识库检索长文问答
Command
分类：语言模型 / 上下文：0.004K / 调用名：command
An instruction-following conversational model that performs language tasks with high quality, more reliably and with a longer context than our base generative models.
能力标签未整理
语言模型语义检索RAG向量搜索
Embed v4.0
分类：语言模型 / 上下文：0.128K / 调用名：embed-v4.0
A model that allows for text and images to be classified or turned into embeddings
视觉
语言模型语义检索RAG向量搜索
Embed English v3.0
分类：语言模型 / 上下文：0.512K / 调用名：embed-english-v3.0
A model that allows for text to be classified or turned into embeddings. English only.
能力标签未整理
语言模型语义检索RAG向量搜索
Embed English Light v3.0
分类：语言模型 / 上下文：0.512K / 调用名：embed-english-light-v3.0
A smaller, faster version of embed-english-v3.0 . Almost as capable, but a lot faster. English only.
能力标签未整理
语言模型语义检索RAG向量搜索
Embed Multilingual v3.0
分类：语言模型 / 上下文：0.512K / 调用名：embed-multilingual-v3.0
Provides multilingual classification and embedding support. See supported languages here.
能力标签未整理
语言模型语义检索RAG向量搜索
Embed Multilingual Light v3.0
分类：语言模型 / 上下文：0.512K / 调用名：embed-multilingual-light-v3.0
A smaller, faster version of embed-multilingual-v3.0 . Almost as capable, but a lot faster. Supports multiple languages.
能力标签未整理
语言模型搜索排序RAG 检索结果重排
Rerank v4.0 Pro
分类：语言模型 / 上下文：0.032K / 调用名：rerank-v4.0-pro
A multilingual model that allows for re-ranking English and non-english documents and semi-structured data (JSON). This is better suited for state-of-the-art quality and complex use-cases than its fast variant.
结构化输出
语言模型搜索排序RAG 检索结果重排
Rerank v4.0 Fast
分类：语言模型 / 上下文：0.032K / 调用名：rerank-v4.0-fast
A light version of rerank-v4.0-pro , this is a multilingual model that allows for re-ranking English and non-english documents and semi-structured data (JSON). This model is better suited for low latency and high throughput use-cases than its pro variant.
结构化输出
语言模型搜索排序RAG 检索结果重排
Rerank v3.5
分类：语言模型 / 上下文：4.096K / 调用名：rerank-v3.5
A model for documents and semi-structured data (JSON). Performs well in English and non-English languages; supports the same languages as embed-multilingual-v3.0. This model has a context length of 4096 tokens
结构化输出
语言模型搜索排序RAG 检索结果重排
Rerank English v3.0
分类：语言模型 / 上下文：4.096K / 调用名：rerank-english-v3.0
A model that allows for re-ranking English Language documents and semi-structured data (JSON). This model has a context length of 4096 tokens.
结构化输出
语言模型搜索排序RAG 检索结果重排
Rerank Multilingual v3.0
分类：语言模型 / 上下文：4.096K / 调用名：rerank-multilingual-v3.0
A model for documents and semi-structure data (JSON) that are not in English. Supports the same languages as embed-multilingual-v3.0 . This model has a context length of 4096 tokens.
能力标签未整理
语音模型语音转写会议整理音频理解
Cohere Transcribe
分类：语音模型 / 上下文：- / 调用名：cohere-transcribe-03-2026
This page describes how the Cohere Transcribe model works and how to use it.
语音输入
语言模型多语言应用全球化业务跨语种问答
Tiny Aya Global
分类：语言模型 / 上下文：0.008K / 调用名：tiny-aya-global
Tiny Aya Global is a 3.35B instruction-tuned multilingual model with the best balance across languages and regions. Supports 70 languages.
能力标签未整理
语言模型多语言应用全球化业务跨语种问答
Tiny Aya Earth
分类：语言模型 / 上下文：0.008K / 调用名：tiny-aya-earth
Tiny Aya Earth is a 3.35B region-specialized multilingual model, best for West Asian and African languages. Supports 70 languages.
能力标签未整理
语言模型多语言应用全球化业务跨语种问答
Tiny Aya Fire
分类：语言模型 / 上下文：0.008K / 调用名：tiny-aya-fire
Tiny Aya Fire is a 3.35B region-specialized multilingual model, best for South Asian languages. Supports 70 languages.
能力标签未整理
语言模型多语言应用全球化业务跨语种问答
Tiny Aya Water
分类：语言模型 / 上下文：0.008K / 调用名：tiny-aya-water
Tiny Aya Water is a 3.35B region-specialized multilingual model, best for European and Asia-Pacific languages. Supports 70 languages.
能力标签未整理
语言模型多语言应用全球化业务跨语种问答
Aya Expanse 32B
分类：语言模型 / 上下文：0.128K / 调用名：c4ai-aya-expanse-32b
Aya Expanse is a highly performant 32B multilingual model, designed to rival monolingual performance through innovations in instruction tuning with data arbitrage, preference training, and model merging. Serves 23 languages.
能力标签未整理
多模态模型视觉理解图文问答多语言任务
Aya Vision 32B
分类：多模态模型 / 上下文：0.016K / 调用名：c4ai-aya-vision-32b
Aya Vision is a state-of-the-art multimodal model excelling at a variety of critical benchmarks for language, text, and image capabilities. Serves 23 languages. This 32 billion parameter variant is focused on state-of-art multilingual performance.
视觉
语言模型多语言应用全球化业务跨语种问答
Aya Expanse 8B
分类：语言模型 / 上下文：0.128K / 调用名：c4ai-aya-expanse-8b
Aya Expanse is a highly performant 32B multilingual model, designed to rival monolingual performance through innovations in instruction tuning with data arbitrage, preference training, and model merging. Serves 23 languages.
能力标签未整理
多模态模型视觉理解图文问答多语言任务
Aya Vision 8B
分类：多模态模型 / 上下文：0.016K / 调用名：c4ai-aya-vision-8b
Aya Vision is a state-of-the-art multimodal model excelling at a variety of critical benchmarks for language, text, and image capabilities. Serves 23 languages. This 32 billion parameter variant is focused on state-of-art multilingual performance.
视觉
多模态模型视觉理解多语问答轻量部署
North Micro Vision Instruct
分类：多模态模型 / 上下文：32.768K / 调用名：north-micro-vision-instruct
North Micro Vision Instruct 是 Cohere 于 2026 年 8 月公开的轻量多语视觉模型，适合图像理解、视觉问答和本地部署。
视觉推理multilingual开放权重
语音模型阿拉伯语识别方言转写多语语音
Cohere Transcribe Arabic
分类：语音模型 / 上下文：4.096K / 调用名：cohere-transcribe-arabic-07-2026
Cohere Transcribe Arabic 是 Cohere 于 2026 年 6 月公开的阿拉伯语语音识别模型，支持阿拉伯语方言和英语混合转写。
asrspeech_recognitionmultilingual开放权重结构化输出语音输入