Get started in minutes
Install the CLI and go from an empty directory to a deployed model in a few
minutes.
What you can do
Fine-tune a model on your own task
Write a TOML config, run one command, and Flash trains a LoRA adapter (a small set of add-on weights) on top of a supported base model. Pick the model and task; Flash handles the training infrastructure. See Training.Teach a format from examples with SFT
Supervised fine-tuning learns from the prompt/answer pairs in your dataset. Use it when you already have examples of the output you want.Reward the behavior you want with GRPO
Reinforcement learning scores the model’s own completions with your environment’s reward, then updates toward higher-scoring completions (see How Flash works). Use it when you can score an output but can’t hand-write the perfect one.Distill a stronger model with OPD
On-policy distillation has a managed teacher (GLM 5.2 by default) grade your model’s own completions token by token, then pulls your model toward it. Use it when a bigger model already does the task and you want a small one to match it — no answers to write and no reward to design.Serve it behind an OpenAI-compatible API
flash deploy registers the adapter with managed serving, then
flash chat or any OpenAI client can call it with your Freesolo key. See
Deploy & chat.
See the cost before you spend
--cost prints the pre-flight estimate without submitting. You pay for the
quoted training run cost and for the tokens you serve. Cancelled runs are
repriced to the training steps they actually reached.
Where Flash fits
Next steps
Quickstart
Install the CLI, log in, and ship your first run in a few minutes.
How Flash works
The loop behind a run: base models, environments, algorithms, serving.
Training
Write a config, submit a run, and follow it to completion.
Deploy & chat
Serve an adapter, then chat with it over an OpenAI-compatible API.