Sail serves the reference model by default. Any quantization is called
out explicitly, and we always link to the exact weights we’re using.
Core models
| Model | Model ID | Image | LoRA | Reasoning |
|---|---|---|---|---|
ReferenceView checkpoint | ||||
ReferenceView checkpoint | ||||
NVIDIA quantView checkpoint | ||||
ReferenceView checkpoint | ||||
ReferenceView checkpoint | ||||
ReferenceView checkpoint | ||||
ReferenceView checkpoint | ||||
NVIDIA quantView checkpoint | ||||
ReferenceView checkpoint |
Flex-only models
Models served with the Flex service tier exclusively.| Model | Model ID | Image | LoRA | Reasoning |
|---|---|---|---|---|
ReferenceView checkpoint |
Notes
- If we offer multiple quantizations of a model, we list them as separate model IDs.
- Use
GET /v1/modelsto confirm runtime availability for your API key. - For per-model rates by service tier, see Pricing.