Skip to main content
ModelSlugImageReasoning
DeepSeek V4 Pro
DeepSeek
deepseek-ai/DeepSeek-V4-Pro
Nemotron Ultra
NVIDIA
nvidia/nemotron-3-ultra-550b-a55b
DeepSeek-V4-Flash-0731
DeepSeek
deepseek-ai/DeepSeek-V4-Flash
Kimi K2.7 Code
Moonshot AI
moonshotai/kimi-k2.7-code
Kimi-K3
Moonshot AI
moonshotai/Kimi-K3
GLM-5.2
Z.ai
zai-org/GLM-5.2-FP8
GLM-5.2 Fast
Z.ai
zai-org/GLM-5.2-Fast
gpt-oss-120b
OpenAI
openai/gpt-oss-120b
Qwen3.5-397B-A17B
Qwen
Qwen/Qwen3.5-397B-A17B
Qwen3.6 35B-A3B
Qwen
Qwen/Qwen3.6-35B-A3B
Gemma 4 31B IT
Google
google/gemma-4-31B-it
Gemma 4 26B A4B
Google
google/gemma-4-26B-A4B-it
MiniMax M2.7
MiniMax
MiniMaxAI/MiniMax-M2.7
MiniMax M3
MiniMax
MiniMaxAI/MiniMax-M3

​
Custom models

Beyond the catalog above, Valar can serve your own model weights. If you have a custom or fine-tuned open-weight model, we can host it on Valar’s inference stack and expose it through the same OpenAI-compatible API, completion windows, and billing as any catalog model. Reach out to your Valar contact to onboard a custom model. For adapter-based customization on top of a supported base model, register a PEFT-trained LoRA adapter and run it against an eligible base model such as zai-org/GLM-5.2.
To confirm what your API key can reach in a given environment at runtime, call GET /v1/models against that environment rather than relying on this table alone.