Hacker News Reader

Comment by davidvgilmore | Hacker News Reader

thanks for the feedback. To understand the preference - would you prefer to (1) bring your own keys or (2) use different models?

Regarding (2), we haven't supported other models yet because they each come with their own peculiarities regarding system prompting / tool use / etc. By focusing on just Sonnet+Haiku, it's allowed us to focus more time on other features (e.g. checkpointing ...).

Regarding BYOKs - a lot of our beta users didn't actually have keys setup, so it was easier for them to get started without bringing their own keys. The folks that have been interested in BYOKs have mainly wanted to bring their Bedrock/Vertex keys and are interested in enterprise/team features. Hence structuring it this way.

But we're posting here to get feedback and we are willing to make changes :)

View on HN

Where I work, our legal department requires making use of LLMs only through our own contractual relationships with model providers. Given that, BYOK is table stakes for me at least.

Litellm is what we use internally, so we can support any LLM backend with any open source tool, and create virtual keys for each developer to monitor and manage usage limits etc.

helpful context.

yeah - we want to get the BYOK support to be self-service but we just prioritized other things based on user feedback.

thanks again for the context.

> (2) use different models?

Primarily this. Models are evolving fast, every 2 months we see a model emerging with new interesting features. I want to be able to easily switch and try them.

Got it. Helpful.

Our roadmap is essentially this: [1] Additional model support (e.g. Gemini 2.5). [2] MCP support. [3] Computer use.

so in the near future we aim to have the top agentic coding models supported

Bringing your keys is critical for any enterprise use. I’m surprised you have users at Google since utilizing non-gemini models there is a no-no. I would love to try, but as the other user said we use litellm so there isn’t any way to use this. The big plus with Claude code is it allows bedrock use. Codex works with litellm assuming you disable the responses. I don’t think you can reasonably call this a CC competitor until you allow for more open use. I get that it messes up making money — but both codex/cc don’t require I I sign up for anything extra.

thanks - yeah, we've heard this feedback loud and clear from the HN community.

We're cooking

Reply on news.ycombinator.com