Meta in Flintr
Llama, or your own fine-tune of it.
Meta's Llama models are the most widely used open-weight family. Use the hosted versions in your plan, or connect an endpoint your team already runs.
Available models
Llama models in every paid plan.
Llama
Self-hostableBest for: Open-weight general coding and chat
Why developers pick it
What Llama is good at.
Bring your own endpoint
Point Flintr at an OpenAI-compatible endpoint your team runs, including fine-tuned Llama models.
Widely supported
The biggest ecosystem of open-weight tooling, fine-tunes and community knowledge.
No lock-in
Open weights mean the model you rely on can't disappear behind a policy change.
How Auto uses Llama. Llama isn't part of Auto's default pool. Pin it per project or connect your own endpoint in settings. How Auto chooses.
FAQ
Llama in Flintr, answered.
Is Llama included in Flintr Pro?
Yes. Every paid plan includes model usage that you can spend on any model, including Llama. Hobby includes limited access to fast models.
How much does Llama cost in Flintr?
Requests first draw from your plan's included usage. After that they're billed at Meta's published per-token list price with no markup. The cost of every request is shown in the editor.
Can I use my own Meta API key?
Yes. Add your key in settings and choose whether Llama requests use your key or your included usage. Requests on your own key never count against your plan.
Will Meta train on my code?
No. Privacy mode is on by default and we have zero-data-retention agreements with every model provider, including Meta. Your code isn't stored or used for training.
Llama, and everything else. One bill.
Flintr is in development and funded by the people who'll use it. Back the launch from €5, or from €25 to get into the private beta.
Coming to macOS 12+ · Windows 10+ · Linux (deb, rpm, AppImage)