'%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
August 12, 2026 · Together AI
Qwen3.8-2.4T-A95B now available on serverless, in FP4 quantization
The following models are now available on serverless:
Qwen/Qwen3.8-2.4T-A95B: FP4 quantization. Pricing: $2.50 input / $6.25 output / $0.50 cached input (per 1M tokens).
Related updates
Qwen3.8-Flash on serverless with 1M context, at $0.15 input / $0.47 output per 1M tokens
Muse-Spark-Open-816B-A42B and Nemotron-3.5-Super-VL available on serverless
GLM-5.3 on serverless with 1M context, at $1.40 input / $4.40 output per 1M tokens
AI Search - New Workers AI text generation models in AI Search · Cloudflare