~/MICROSOFT FO/microsoft-enables-kimi-k3-deployment-on-microsoft-foundry-via-fireworks-ai

Microsoft Enables Kimi K3 Deployment on Microsoft Foundry via Fireworks AI

Microsoft has announced that users can now deploy Moonshot AI's Kimi K3 model on the Microsoft Foundry platform through Fireworks AI. This integration allows developers to run the massive 2.8-trillion-parameter model within Microsoft's enterprise AI ecosystem. This partnership provides enterprise developers with streamlined access to one of the largest open models available, combining Microsoft's robust management tools with Fireworks AI's high-speed, cost-effective inference. It reflects the growing trend of cloud providers integrating diverse, high-performance open-source models to attract enterprise AI workloads. The Kimi K3 model features a 1-million-token context window, capable of processing approximately 750,000 words in a single request. Under the Data Zone deployment type, pricing is set at $3.30 per million input tokens, $16.50 per million output tokens, and $0.33 per million cached input tokens.

## BACKGROUND

Microsoft Foundry (now Azure AI Foundry) is an integrated platform that simplifies building, testing, and deploying AI applications and agents. Fireworks AI is a specialized cloud platform founded by former PyTorch core team members that optimizes the speed and cost-efficiency of serving large language models. Moonshot AI's Kimi K3 is a frontier open-source model that pushes the scaling limits of open weights.

## REFERENCES

## KEYWORDS

#Microsoft Foundry#Kimi K3#Fireworks AI#LLM Deployment

$ subscribe --daily

Microsoft Enables Kimi K3 Deployment on Microsoft Foundry via Fireworks AI | Daily News