Skip to content

Cloud Changelog

July 20, 2026 · Together AI

DeepSeek-V4-Flash available for deployment on dedicated endpoints

The following models are now available for deployment on dedicated endpoints:

deepseek-ai/DeepSeek-V4-Flash.

Read the Together AI changelog

Latest Together AI platform changes

Nov 12, 2026
Serverless model with 1,048,576-token context, NVFP4 quantization, text and image input, function calling, structured… GA
Nov 10, 2026
Added to serverless with 262,144 context, FP8, function calling, structured outputs
Nov 5, 2026
moonshotai/Kimi-K3.1-Pro on serverless, with 1,048,576-token context
Nov 4, 2026
Kimi-K3.1-Pro available for LoRA post-training on B200-SXM
Nov 3, 2026
MiniMax M3.1 Flash adapters can be deployed on dedicated model inference

All Together AI platform changes