Skip to main content

​
Core models

ModelSlugImageLoRAReasoning
GLM-5.2
Z.ai
zai-org/GLM-5.2-FP8
DeepSeek V4 Flash 0731
DeepSeek
deepseek-ai/DeepSeek-V4-Flash-0731
Kimi-K2.6
Moonshot AI
moonshotai/Kimi-K2.6
gpt-oss-120b
OpenAI
openai/gpt-oss-120b
Gemma 4 31B IT
Google
google/gemma-4-31B-it
Gemma 4 31B IT (NVFP4)
Google
nvidia/Gemma-4-31B-IT-NVFP4

​
Flex-only models

Models served with the flex completion window exclusively.
ModelSlugImageLoRAReasoning
Qwen3.6 35B A3B
Qwen
Qwen/Qwen3.6-35B-A3B
Nemotron 3 Super 120B A12B BF16
NVIDIA
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16

​
Notes

  • Each row links the exact Hugging Face checkpoint Sail currently serves. If we offer multiple quantizations, we list them as separate model IDs.
  • This table and GET /v1/models return canonical model IDs only. Sail may continue accepting an older ID as a compatibility alias, but new requests should use the canonical slug shown here.
  • Use GET /v1/models to confirm runtime availability for your API key.
  • For per-model rates by completion window, see Pricing.