'%3e%3crect%20x='16'%20y='51'%20width='68'%20height='27'%20rx='13.5'/%3e%3ccircle%20cx='32'%20cy='53'%20r='15'/%3e%3ccircle%20cx='53'%20cy='43'%20r='20'/%3e%3ccircle%20cx='71'%20cy='57'%20r='12'/%3e%3c/g%3e%3c/svg%3e){kind=small}
Cloud Changelog
September 11, 2026 · Together AIDeprecation
Three models deprecated for fine-tuning, including Nemotron-3 and Qwen3.5-35B-A3B-Base
The following models have been deprecated and are no longer available for fine-tuning:
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16.nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16.Qwen/Qwen3.5-35B-A3B-Base. Recommended replacement:Qwen/Qwen3.5-35B-A3B.
Related updates
Four models deprecated on serverless, including DeepSeek-V4-Pro and Kimi-K2.7-Code
gpt-oss-20b, gemma-4-31B-it and two other models deprecated on serverless
Fine-tuning training quality improves for Qwen3.5, Qwen3.6 and Nemotron 3 models
Workers AI - Planned model deprecations on Workers AI · Cloudflare