The engines that answer typed, calibrated decisions
Several engines answer the same questions and return the same answer shapes.A diffusion read seeds a canvas and denoises it once. A generative read writes the answer template under a grammar. Nothing is parsed. An answer cannot be off-schema.
Model
Read
Notes
google/diffusiongemma-26b-a4b-it
diffusion
The default engine, and the most peaked distributions.
google/gemma-4-26b-a4b-it
generative
The sparse sibling of the default: 4B active, so a read costs a fraction of its size.
qwen/qwen3.8-27b
generative
The largest generative engine on this route.
qwen/qwen3.5-0.8b
generative
The smallest engine on this route. Decisions are less peaked than the default’s.
Each id also accepts its Hugging Face spelling, such as Qwen/Qwen3.8-27B.
Generative reads are experimental: The diffusion engine reads probabilities straight off the canvas. The shape is guaranteed. The calibration is not. On the smaller engines, measured probabilities sit much closer to uniform. A confident-looking answer can still be wrong. Treat confidence from a generative read as a weak signal. Validate on your own labelled data before you threshold on it. Prefer google/diffusiongemma-26b-a4b-it wherever the decision matters.
There is no catch-all alias: Name the model you want. An id the deployment does not serve is a 404. Override the TypeSafe SDK’s jev-latest default. See TypeSafe SDK Compatibility.
Which engines a deployment serves varies. A decision reports the id that answered it. Read the live list: GET /typesafe/v1/models. Do not hard-code an id.
