Token导航 LogoToken导航TokenDH.com

官方模型目录与价格对比

找模型,不只看名字,还要看 能力和价格

按模型类型、上下文、价格和厂商整理官方模型目录,方便你快速筛出适合写代码、做推理、跑视觉或搭 Agent 的那一批模型。

先缩小候选,再进详情页看接口、计费和能力边界。

已收录模型

1,303

覆盖厂商

63

带价格信息

355

语言模型阶跃稳定版

step-3.5-flash-2603

基于 Step 3.5 Flash 针对高频 Agent 场景优化,在保留旗舰推理与工具调用能力的同时,进一步提升 Token 效率与推理速度,并支持切换低推理模式以降低消耗。对 Coding 与 Agent 框架兼容性也做了专项优化。

输入价格

公开资料未说明

输出价格

公开资料未说明

推理Agent低推理模式
语言模型阶跃稳定版

step-3.5-flash

旗舰级推理模型,专为智能体构建而生。推理深度比肩顶尖闭源模型,同时具备极速响应与稳定可靠的工具调用能力。在通用推理能力基础之上,更擅长复杂项目规划与长程任务执行。

输入价格

¥0.70 / 1M Tokens

输出价格

¥2.10 / 1M Tokens

推理工具调用深度推理
语言模型Cohere稳定版

Command A

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.

输入价格

公开资料未说明

输出价格

公开资料未说明

Agent知识库检索长文问答
语言模型Cohere稳定版

Command R7B

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.

输入价格

公开资料未说明

输出价格

公开资料未说明

Agent知识库检索长文问答
语言模型Cohere稳定版

Command A Reasoning

Command A Reasoning excels in tool use, agentic workflows, and complex problem-solving. It has 111 billion parameters and a 256k context length.

输入价格

公开资料未说明

输出价格

公开资料未说明

复杂推理多步任务Agent
语言模型Cohere稳定版

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.

输入价格

公开资料未说明

输出价格

公开资料未说明

Agent知识库检索长文问答
语言模型Cohere稳定版

Command R+ 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.

输入价格

公开资料未说明

输出价格

公开资料未说明

Agent知识库检索长文问答
语言模型Cohere即将下线

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.

输入价格

公开资料未说明

输出价格

公开资料未说明

Agent知识库检索长文问答
语言模型Cohere即将下线

Command R+ 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.

输入价格

公开资料未说明

输出价格

公开资料未说明

Agent知识库检索长文问答
语言模型Cohere即将下线

Command R+

Command R+ is Cohere's optimized for conversational interaction and long-context tasks, best suited for complex RAG workflows and multi-step tool use.

输入价格

公开资料未说明

输出价格

公开资料未说明

Agent知识库检索长文问答
语言模型Cohere即将下线

Command R

Command R is a conversational model that excels in language tasks and supports multiple languages, making it ideal for coding use cases.

输入价格

公开资料未说明

输出价格

公开资料未说明

Agent知识库检索长文问答
语言模型Cohere即将下线

Command Light

A smaller, faster version of command . Almost as capable, but a lot faster.

输入价格

公开资料未说明

输出价格

公开资料未说明

Agent知识库检索长文问答
语言模型Cohere即将下线

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.

输入价格

公开资料未说明

输出价格

公开资料未说明

Agent知识库检索长文问答
语言模型Cohere稳定版

Embed v4.0

A model that allows for text and images to be classified or turned into embeddings

输入价格

公开资料未说明

输出价格

公开资料未说明

语义检索RAG向量搜索
语言模型Cohere稳定版

Embed English v3.0

A model that allows for text to be classified or turned into embeddings. English only.

输入价格

公开资料未说明

输出价格

公开资料未说明

语义检索RAG向量搜索
语言模型Cohere稳定版

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.

输入价格

公开资料未说明

输出价格

公开资料未说明

搜索排序RAG 检索结果重排
语言模型Cohere稳定版

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.

输入价格

公开资料未说明

输出价格

公开资料未说明

搜索排序RAG 检索结果重排