需求卡片 #392 · 相关性 中 · 新发现

支持订阅制 LLM 提供商的集成

更新于 2026/10/10 22:14:11

问题概述

用户希望将多代理编排工具与其已有的订阅制大模型服务(如 Claude、Codex、Ollama Cloud)兼容,但目前工具缺乏对这些服务的直接支持,迫使用户依赖 API 密钥或放弃使用。同时用户对定价模型(订阅 vs API)和代理编排的阈值(如上下文窗口压缩)有疑问。

痛点标签

待验证问题

证据

原话 · @Anonymous
I don't mind paying for intelligence, but coding agents are expensive and at this time I am nearly exclusively using subscriptions for them, until the math (inevitably) changes.
原话 · @Anonymous
I really wanted to try it, but I couldn't find Ollama Cloud among the options. Most of my subscriptions are official Claude and Codex subscriptions, not API key accounts.
原话 · @Anonymous
I like the ideas here. I would like to test it out with my subscription. Is that something you plan on supporting?

免责声明:本卡片由 AI 从社区讨论中提炼,属于「痛点证据」,是需求分析与验证的起点,不等同于「已验证的市场需求」。AI 存在分析局限,关键决策前请打开上方原始讨论人工复核。