您可以在 OpenClaw 上使用的免费模型（无需信用卡）
我们整理了一份可以通过Manifest今天连接到OpenClaw的免费模型列表。无需信用卡，也没有3天后过期的试用期。只需获取一个API密钥即可开始使用。
以下是可用的模型：
- Google Gemini - 包含5个模型，包括gemini-2.5-pro和gemini-2.5-flash。所有模型每分钟最多可处理250K个令牌。专业版模型在免费层级下具有1M的上下文窗口。
- Cohere - 包括command-a-03-2025和command-a-reasoning-08-2025。每月1000次调用，256K上下文。
- Kilo Code - 包含4个模型，包括Qwen 3.6 Plus、Nemotron 3 Super 120B和Step 3.5 Flash。每小时约200次请求。部分模型支持图像和视频输入。
整个目的就是让您在不花费任何费用的情况下开始使用。连接一两个免费提供者，设置一个带有回退机制的路由配置，您就已经有了一个可用的设置。如果Gemini达到速率限制，Manifest会自动回退到Cohere或Kilo Code。
更多即将上线的可设置免费模型正在筹备中，所有模型都在这里列出：https://manifest.build/free-models
我们仍处于测试阶段，积极尝试了解人们如何使用这个平台。您的设置是怎样的？您正在使用哪些提供者？如果您遇到任何问题或有反馈，我们非常希望听到您的声音。
查看原文
We put together a list of free models you can connect to OpenClaw today through Manifest. No credit card, no trial that expires after 3 days. Just grab an API key and go.<p>Here's what's available:<p>- Google Gemini - 5 models including gemini-2.5-pro and gemini-2.5-flash. Up to 250K tokens per minute across all models. The pro model has a 1M context window on the free tier.<p>- Cohere - command-a-03-2025 and command-a-reasoning-08-2025. 1,000 calls per month, 256K context.<p>- Kilo Code - 4 models including Qwen 3.6 Plus, Nemotron 3 Super 120B, and Step 3.5 Flash. Around 200 requests per hour. Some support image and video input.<p>The whole point is to get started without spending anything. Connect one or two free providers, set up a routing config with fallbacks, and you already have a working setup. If Gemini hits its rate limit, Manifest falls back to Cohere or Kilo Code automatically.<p>More ready-to-setup free models are coming. hey are all listed here: https://manifest.build/free-models<p>We're still in beta and actively trying to understand how people use this. What does your setup look like? What providers are you using? If you run into anything weird or have feedback, we want to hear it.