Skip to main content
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

ModelModel IDImageLoRAReasoning
Kimi K3.1 Pro
Moonshot AI
GLM-5.3
Z.ai
GLM-5.3-Flash
Z.ai
NVIDIA quantView checkpoint
DeepSeek V4.1 Flash 1017
DeepSeek
DeepSeek V4 Pro 0813
DeepSeek
DeepSeek V4 Flash 0731
DeepSeek
Gemma 4 31B IT
Google
Gemma 4 31B IT (NVFP4)
Google
NVIDIA quantView checkpoint
Gemma 4 12B IT
Google

Flex-only models

Models served with the Flex service tier exclusively.
ModelModel IDImageLoRAReasoning
Qwen3.6 35B A3B
Qwen

Notes

  • If we offer multiple quantizations of a model, we list them as separate model IDs.
  • Use GET /v1/models to confirm runtime availability for your API key.
  • For per-model rates by service tier, see Pricing.