# Changes to Bring Your Own AI in v2 Bring Your Own AI features are now part of Raycast Pro in Raycast v2. Learn what's changing, why, and what it means for you. Hey, Thomas here. With Raycast v2, Bring Your Own AI features require Raycast Pro. That includes Bring Your Own Keys, Custom Providers, and Local Models. I can see why "pay us so I can use my own key" feels strange. We shared that decision without explaining the broader pricing direction or the product changes behind it, and we should have communicated this better. I want to provide a bit more context and be clear about what is decided today and where we're heading. ## Why We're Changing Pricing We launched Raycast Pro in May 2023 as a paid subscription. As part of it, you got Raycast AI, Cloud Sync, custom themes, and extended Clipboard History. A big part of the Pro plan was access to all LLMs. Since then, the AI landscape has changed significantly. There are many more models, their costs vary considerably, and agentic loops have increased usage substantially. We tried bundling the Raycast product and all inference into one flat subscription, but with growing token usage, that no longer seems sustainable. So we took a step back and looked at the value Raycast itself provides. ## Raycast as the Interface Layer Raycast has always been about building a better interface on top of your existing tools. We think the clearest principle is that Raycast should be the interface layer, not the inference layer. We spend our time making that interface as useful as possible, from the Launcher through Dictation and Notes to AI Chat. With v2, we're rebuilding our AI system, adding memory, projects, automations, and more capable ways for AI to complete work for you. With that in mind, we want to separate the value Raycast provides from the underlying inference costs. The Raycast subscription pays for the product around the model: the interface, context, integrations, tools, and execution layer. How the intelligence underneath it is supplied should become a separate and transparent choice. I feel this aligns our incentives much better because our business succeeds by making Raycast better, not by maximizing a margin on tokens. I also understand that changing an existing feature is frustrating and potentially disruptive, especially for people who have already built their workflow around BYOK, Custom Providers, or Local Models. ## What This Means in Practice In v2, there are four ways to use AI through Raycast Pro: **Built-in models:** We continue providing access to LLMs through Raycast for convenience. We're also exploring a more transparent usage-based model, but the details aren't final yet. **Bring Your Own Keys:** You can [bring your own key](https://manual.raycast.com/ai/bring-your-own-keys) for OpenAI, Anthropic, Google, or OpenRouter. We've seen many people use API keys provided by their employers. **Custom Providers:** You can [connect any OpenAI-compatible provider](https://manual.raycast.com/ai/custom-providers), from cloud gateways and team proxies to agents running on your machine. We see Custom Providers used mostly in enterprise environments, but they're available to everyone on Pro. **Local Models:** You can [run models on your own machine](https://manual.raycast.com/ai/local-models) through Ollama, with nothing leaving your computer. Longer term, we want to offer more ways to supply the intelligence underneath Raycast: **Existing subscriptions:** Many people already pay for ChatGPT or Claude, and we don't want to force them to purchase the same underlying AI capabilities again through Raycast. We're working on ways to bring some of those existing subscriptions into Raycast. All of these options use the same Raycast product around the model, which is why they require a Pro subscription in v2. Your API key or existing subscription covers the LLM. Raycast Pro covers the interface, context, integrations, tools, and execution layer around it. We offer a free 7-day Pro trial with no credit card required, so you can decide whether the product around the model is valuable to you. This is the current plan for v2, and we'll publish the complete pricing before these changes roll out more broadly. ## Going Forward The industry is in a weird state. Many startups subsidize tokens to grow, but that isn't the route we want to take. We see Raycast as a fundamental tool for many professionals and feel responsible for building a sustainable business that can control its own future and keep the product around for a long time. For us, sustainability means charging for the value the product creates without betting on tokens becoming cheaper in the future. It also means being honest about the distinction between the model costs and the ongoing work required to build and maintain Raycast. This is why we chose a recurring subscription instead of a one-time payment. We ship updates every week and want the business model to align with that continued development. This isn't a plan to put all of Raycast behind a paywall. As before, the Launcher and the vast majority of the core Raycast experience will remain free. We haven't figured out every detail yet, and I understand that this pricing model won't work for everyone. But I hope the reasoning and where we're heading are clearer now. I'd love to hear your feedback, especially about how you use BYOK, Custom Providers, or Local Models today and what feels right to you. Use the [Send Feedback](raycast://extensions/raycast/raycast/send-feedback) command in Raycast to reach us directly, or contact us at [support@raycast.com](mailto:support@raycast.com).
Thomas Paul Mann
Co-founder, Raycast
## FAQ ### Why do I need Pro to use my own key or a model on my own machine? Your key or your hardware covers the model. Raycast Pro covers everything around it: the interface, context, integrations, tools, and execution layer. All of these options use the same Raycast product around the model, whether the intelligence underneath comes from Raycast, your key, or your own machine. ### Does this change affect Raycast v1? No. Nothing changes in v1. Bring Your Own Keys, custom providers, and local models keep working there as before. The change applies to v2 only. ### Do Custom Providers and Local Models need Pro too, or just BYOK? All three. [Bring Your Own Keys](https://manual.raycast.com/ai/bring-your-own-keys), [Custom Providers](https://manual.raycast.com/ai/custom-providers), and [Local Models](https://manual.raycast.com/ai/local-models) are all part of Raycast Pro in v2, because they all use the same Raycast product around the model. ### How much does Raycast Pro cost? Go to [raycast.com/pricing](https://raycast.com/pricing) for the latest pricing information. One Pro subscription works across macOS, Windows, and iOS. There's a free 7-day trial with no credit card required, and we offer a student discount. ### Can I pay once instead of subscribing? We understand the appeal, and it's one of the most common requests we hear. The reason we've stuck with a subscription is that Raycast changes every week. The product you'd pay for today looks quite different a few months later, and a subscription is what lets us keep building it at that pace. We'd rather be upfront about that than sell a one-time license for a product that keeps moving. ### Will there be a cheaper plan with BYOK but without Raycast's built-in AI? Not right now. We've heard this request a lot and we're not ruling it out, but there are no immediate plans. Right now we're focused on rolling out v2 to everyone and supporting our suite of AI features in Raycast. ### If I have Pro and my own API key, which one does Raycast use? When you've added your API key to Raycast in **Settings → AI**, requests for that provider's models go through your API key, and a key icon shows next to those models in the model picker. Otherwise, requests go through Raycast AI using your Raycast Pro subscription. ### My API key gives me access to a model that's only in Advanced AI. Do I still need Advanced AI? Ideally you get access to every model your API key has access to. We're still working out the details here, and the Advanced AI plan is likely to change as a result. ### Did anything change about the privacy of Local Models or my own API keys? No. This change is about pricing only. Local Models requests still run entirely on your machine. If you use Cloud Sync, your chat history syncs encrypted to your other devices, the same as any other chat. Requests to your own API keys and custom providers still go directly to the provider without passing through Raycast's servers. See [Raycast AI Privacy & Security](https://manual.raycast.com/ai/raycast-ai-privacy-security) for the details. ### Are you moving to usage-based pricing? We're exploring a more transparent usage-based option for built-in models, but the details aren't final. Bringing your own key, provider, or local model already gives you usage-based costs directly with the provider, with none of it counting against [Raycast AI usage limits](https://manual.raycast.com/ai/usage-limits). ### Will you move to regional pricing? Nothing is planned this year. We want to support our global community as much as we can, but it's difficult for a team our size to do everything at once. ### I don't use AI in Raycast. Can I hide it? Yes. You choose during onboarding whether to turn on AI features, and you can turn them off any time in **Settings → AI**. To remove the Quick AI command from Root Search, select it, press `⌘ K`/`Ctrl K`, and choose **Disable Command**. ## Bring Your Own AI in Raycast - [Bring Your Own Keys](https://manual.raycast.com/ai/bring-your-own-keys): Use your own Anthropic, Google, OpenAI, or OpenRouter key - [Local Models](https://manual.raycast.com/ai/local-models): Run AI models on your own machine with Ollama - [Custom Providers](https://manual.raycast.com/ai/custom-providers): Connect any OpenAI-compatible provider - [Privacy & Security](https://manual.raycast.com/ai/raycast-ai-privacy-security): See how we protect your data --- ## Need Help? Contact Raycast Support if you have any questions or would like help with Changes to Bring Your Own AI in v2. Use the **Send Feedback** command directly in Raycast to report bugs and billing issues, log feature requests, or any other queries you would like to speak to us about. You can view all Raycast Support contact options at https://manual.raycast.com/contact-support