Release notes for Foundation Models Catalog

Last update: September 07 2026Open in Markdown

2026

August

• added new models:

  • qwen3.6-27b-nvfp4;
  • qwen3.6-35b-a3b-nvfp4.

  You can view the current list of available models in the control panel: in the top menu, click Products → Foundation Models Catalog;

• we simplified the inference service cost calculation: it is now based solely on GPU consumption. Previously, the cost was determined by several resources: GPU, vCPU, RAM, and disk.

July

• added the ability to sort configurations when creating an inference service. Now, at the configuration selection stage, you can sort them by price or performance in ascending or descending order;

• Foundation Models Catalog is now available in the ru-6 pool. We have also added the ability to select a location in the model catalog when creating an inference service;

• added the ability to connect to an inference service from a private network. Learn more in the Inference Service Connection Types guide.

June

• added new models:

  • google/gemma-4-12B;
  • unsloth/Qwen3.6-35B-A3B-NVFP4;
  • unsloth/Qwen3.6-27B-NVFP4.

  You can view the current list of available models in the control panel: in the top menu, click Products → Foundation Models Catalog.

May

• added new models:

  • openai/gpt-oss-120b;
  • Qwen/Qwen3.6-35B-A3B;
  • Qwen/Qwen3.6-27B;
  • Qwen/Qwen3-Embedding-8B;
  • Qwen/Qwen3-Reranker-8B;
  • deepseek-ai/DeepSeek-OCR-2;
  • zai-org/GLM-ASR-Nano-2512;
  • openai/whisper-large-v3;
  • google/gemma-4-31B;
  • t-tech/T-lite-it-2.1;
  • t-tech/T-pro-it-2.1;
  • intfloat/multilingual-e5-large;
  • BAAI/bge-m3;
  • BAAI/bge-reranker-v2-m3.

  You can view the current list of available models in the control panel: in the top menu, click Products → Foundation Models Catalog.

April

• transitioned Foundation Models Catalog from limited testing (private preview) to public testing (public preview).