I would also like to be able to use my own API keys

Your Cascade "Agent" is great and from what I've seen thus far, I'd gladly keep paying a subscription for it to continue driving and managing memory of codebase and context for whichever LLM via cloud or local Ollama API calls I choose to connect to.

I'm using OpenHands and Cursor to achieve this currently but the Windsurf interface and using the Cascade Agent as a prompt interface is far superior, so make a custom API setting, lighten the load on your servers and give us the feature we need.

When we use our own API keys in Cursor, we lose the ability to access the Compose prompting without a subscription, I have not been as impressed with Cursors underlying agent as with Cascade which is why I would be happy to keep paying your subscription however this may be the technical challenge you are facing with using external API keys since the Cascade agent most likely has a specialized way to interact with the models you offer for credits.

I would like to setup several custom API key settings and be able to switch between them as needed, sometimes I just want haiku 3.5 to do some project initialisation quickly and then I move to larger models for more complex tasks. We create several API keys for each cloud service and model, we are able to do better cost comparatives when reviewing logs and tabulate if a cheaper model actually cost more due to errors and bad loops which we cannot accomplish using your current credit system. We need more insight into how many repeat calls were made and how big the context is, custom API settings allow this.

Dear Windsurf Team, I purchased the Pro Ultimate subscription ($60/month) to support your company's development, but I've found that the current 3,000 Flow Action Credits are insufficient for my usage needs. Considering that at the same price, purchasing two regular Pro accounts (2×$15=$30/month) would provide the same number of Flow Action Credits at half the cost, I suggest doubling the Flow Action Credits for Pro Ultimate to at least 6,000 per month. This would provide value that matches the price and truly meet the needs of advanced users. Thank you for developing this excellent product, and I hope to continue supporting Windsurf's growth.

It is essential, a shame that it is not already available! You have to buy with them!

I completely agree I need Echo Grok it would work great and be able to work directly with the API even more

Surprised this isn't already a feature like on Cursor. We're already paying hundreds of $ for API access from various providers, why can't we just use those? I'm happy to still pay for a Windsurf subscription, and if there's overhead involved you could still charge a (small) fee per intelligence operation.

I want to use my own DeepSeek server, which is free for me. You can charge your subscription fee. And I want to make windsurf run 24 x 7 to fix bugs and use my Google API to search as a call for action configuration without using Claude. How about that?

We really need this feature. It needs to point to our on-prem LLM (e.g., Ollama) or the model of our choice. And it we can't really use it for real work if we don't know when it will decide to run out credit.

My team will switch to Cursor if you don't add this soon.

Building swarm of Windsurf instances. Happy to pay for credits, but require a dozen different LLMs running on Ollama. Low latency by design (hours rather than minutes). We can do this folks!