'%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
October 16, 2026 · Together AI
reflection/Beam-1.0-501B-A23B on serverless, with a 1,048,576-token context
The following models are now available on serverless:
reflection/Beam-1.0-501B-A23B: 1,048,576 context length, NVFP4 quantization, function calling, and structured outputs. Pricing: $0.40 input / $1.20 output / $0.04 cached input (per 1M tokens).
Related updates
elorian-labs/glimpse-1.0 on serverless, with 262,144-token context
reflection/Beam-1.0-501B-A23B available on dedicated endpoints
DeepSeek-V4.1-Flash-1017 on serverless, with a 1M-token context window
Beam model by Reflection is now available on Amazon SageMaker JumpStart and AWS Trainium · AWS
Public Preview: Azure Container Apps serverless GPUs now support Azure AI Foundry models · Azure