# Together AI 推出 Together Link,一键在现有编码智能体中接入开源模型并降费超 50%
> 原标题:Together Link: open models in the harness you already use. Start with one command today.
- 来源:Together AI 研究与产品博客
- 发布时间:2026-10-05T00:00:00.000Z
- AIHOT:https://aihot.news/items/ef2o8x2jh4m8n7ggsq5bc5eag
- 原文:https://www.together.ai/blog/together-link-frontier-quality-open-models-in-the-harness-you-already-use
## 摘要
Together AI 发布 Together Link,把团队已用的编码智能体工具连接到 Together AI 上的开源模型,宣称可节省超过 50% 支出。
## 推荐理由
原文给出支持的工具清单、Auto 路由机制和每会话费用对比方式,读者可评估它能否直接嵌入现有编码智能体工作流。
## 正文 · 中文译文
.jpg)
概述
[Together Link](http://together.ai/link) 将你团队已在使用的 harness 连接到 Together AI 上最好的开放模型,并将你的支出削减 50% 以上。同样的 agent,同样的工作流,账单却只是零头。
编码 agent 如今在工程团队中已司空见惯,而你交给它们的每一项任务,从一行修复到完整重写,往往都运行在同一个高端模型上。规模化之后,成本会迅速攀升:工程组织的支出从每月数万美元到数百万美元不等,全都花在闭源模型上。
开放模型已经大幅缩小了与闭源实验室顶级模型之间的差距。像 Kimi K3 和 GLM 5.3 这样的领先者,如今能以每 token 价格的一小部分处理许多最难的编码任务,而像 GLM 5.3 Flash 和 DeepSeek V4.1 Flash 这样小巧而强大的模型则处理日常编码任务。Together Link 将它们带入你团队已经熟悉的工具中。
## 在你已经工作的地方工作
Together Link 支持 Claude Code、Claude Desktop、Codex(ChatGPT 应用和 CLI 中)、OpenCode 和 Pi。你的团队照常工作:设置和登录保持不变,没有新东西要学,而切回原生闭源模型只需一条命令。你只需几分钟就能在开放模型上跑起来。
## 快速开始
```
curl -fsSL https://link.together.ai/install | bash
```
1. **运行一条命令即可设置 Together Link:**你的 agent 会像以前一样打开,现在通过你的 Together AI API key 连接到 Together AI。[创建一个账户](https://api.together.ai/)以获取 API key。
2. **使用“Auto”让 Together AI Router 挑选模型:**它会读取每个会话的第一个任务,并将其发送到合适的模型:快速修复交给快速、低成本的模型,难题则获得前沿能力。如果你提供 Anthropic key,它会在 Opus 5.5 和 GLM 5.3 之间路由。如果不提供,它会在 GLM 5.3 和 GLM 5.3 Flash 之间路由。路由每个会话只发生一次,因此 prompt 缓存仍能正常工作。
3. **查看每个会话后的节省情况。**按会话跟踪器会显示你的实际支出,以及同一会话在 Opus 5.5 上本会花费多少。
计费使用你现有的 Together API key,按无服务器按量付费或积分包结算。你无需单独签约。
## 构建在开发者已经选择的无服务器平台上
Together Link 运行在 Together 的无服务器推理之上,这正是开发者已经在 OpenRouter 上为这些模型所选择的基础设施。Together AI 在 OpenRouter 上为 DeepSeek V4.1 Flash(40.8%)、GLM 5.3 Flash(28.2%)和 Kimi K3(23.1%)提供了最大份额的 token,整体速度和价格都极具竞争力。(_截至 2026 年 9 月 30 日脚注_)
## 后续步骤
创建一个 [Together AI](https://api.together.ai/) 账户。
阅读我们的 [文档](https://docs.together.ai/docs/togetherlink)。
要在整个工程组织推广? [联系我们的团队](https://www.together.ai/contact-sales),我们会帮你规划。
## 正文 · 原文
.jpg)
Summary
[Together Link](http://together.ai/link) connects the harness your team already uses to the best open models on Together AI and cuts your spend by over 50%. Same agent, same workflow, a fraction of the bill.
Coding agents are now commonplace for engineering teams, and every task you give them, from a one-line fix to a full rewrite, often runs on the same premium model. At scale that gets expensive quickly: engineering orgs are spending anywhere from tens of thousands to millions of dollars a month on closed models.
Open models have meaningfully closed the gap between top models from closed labs. Leaders like Kimi K3 and GLM 5.3 now handle many of the hardest coding tasks at a fraction of the per-token price, while small and capable models like GLM 5.3 Flash and DeepSeek V4.1 Flash handle everyday coding tasks. Together Link brings them into the tools your team already knows.
## Works where you already work
Together Link supports Claude Code, Claude Desktop, Codex (in the ChatGPT app and the CLI), OpenCode, and Pi. Your team keeps working normally: settings and logins stay as they were, there's nothing new to learn, and going back to the native closed models takes one command. You can be up and running on open models in just a few minutes.
## Getting started
```
curl -fsSL https://link.together.ai/install | bash
```
1. **Run one command to set up Together Link:** Your agent opens exactly as before, now connected to Together AI with your Together AI API key. [Create an account](https://api.together.ai/) for an API key.
2. **Use “Auto” to pick a model with the Together AI Router:** It reads each session's first task and sends it to the right model: quick fixes go to fast, low-cost models, and hard problems get frontier capability. If you bring an Anthropic key, it routes between Opus 5.5 and GLM 5.3. Without one, it routes between GLM 5.3 and GLM 5.3 Flash. Routing happens once per session, so prompt caching keeps working.
3. **See your savings after each session.** A per-session tracker shows what you spent next to what the same session would have cost on Opus 5.5.
Billing runs on your existing Together API key, against serverless pay-as-you-go or credit packs. You don't need a separate contract.
## Built on the serverless platform developers already choose
Together Link runs on Together's serverless inference, the same infrastructure developers already pick for these models on OpenRouter. Together AI serves the largest share of OpenRouter tokens for DeepSeek V4.1 Flash (40.8%), GLM 5.3 Flash (28.2%), and Kimi K3 (23.1%), with competitive speed and pricing across the board. (_As of 9/30/2026 footnote_)
## Next steps
Create a [Together AI](https://api.together.ai/) account.
Read our [docs](https://docs.together.ai/docs/togetherlink).
Rolling it out across your engineering org? [Talk to our team](https://www.together.ai/contact-sales) and we'll help you plan it.