The research lab focused on inference.

TrainingAutomatic fine-tuning from your traffic.

InferenceOpen-model inference, pay based on your latency requirement.

Models

NotesFrontier notes on inference, systems and hardware.

MethodsHow we operate, and why.

Latest writing

See all writing

Post training models

DeepSeekDeepSeek V4.1 Flash Z.AIGLM-5.3 Flash Jared PalmerKev 9B

Don't see a model you want? Raise a model request