Catalog
Every catalog model supports SFT, GRPO, and OPD, accepts image inputs for training and serving (see Image inputs), and is hybrid-reasoning: it runs with or without an explicit reasoning step, which you turn on withthinking = true.
The catalog is the whole set of trainable models. A model outside it is
rejected when the config is parsed, before any GPU is rented, and there is no
config key that opts into an uncatalogued id. The error lists the supported ids.
Serving prices
Serving is billed per token after deployment, at the per 1M token rates below. Cached prompt tokens are prompt tokens served from the automatic prefix cache; see Billing for when it applies.Context window and LoRA rank
Every model trains and serves at a 32768-token context - a LoRA trained longer than it is served would learn positions inference never uses.flash train enforces that cap and the per-model max LoRA rank above at submit: a
config whose max_context_tokens exceeds the cap, whose GRPO/OPD prompt plus
max_completion_tokens cannot fit, or whose lora_rank exceeds the max rank, is
rejected.
Choosing a model
Start small
Use
Qwen/Qwen3.5-0.8B or 2B to validate your setup and data cheaply. Get
a run working before you scale.Scale up for quality
Move to
Qwen/Qwen3.5-4B or 9B once the task is wired up and you want
stronger results. Larger models cost more per run.Pick a model, then train
Set
model in your config and submit a run.