- Dec 15, 2025
- 5 min read
Enabling the Next Level of Efficient Agentic AI: FriendliAI Supports NVIDIA Nemotron 3 Nano Launch
Read full article

- January 4, 2026
- 7 min read
Rethinking AI Inference Kubernetes Cluster Consistency with Atomic State Reconciliation
Reliability
Kubernetes
Atomic State Reconciliation

- December 31, 2025
- 2 min read
K-EXAONE Is Now Available on Friendli Serverless Endpoints
LG AI Research
K-EXAONE
Partnership

- December 30, 2025
- 3 min read
Serverless vs. Dedicated AI Inference: Choosing the Right Friendli Endpoint for Your Workload
Serverless Endpoints
Dedicated Endpoints
Inference

- December 19, 2025
- 6 min read
MCP: Ushering in the Era of AI Agents
Model Context Protocol
MCP
AI Agents

- December 16, 2025
- 2 min read
A Faster, Convenient Way to Discover and Deploy AI Models on FriendliAI
Model
Deploy
Update

- December 11, 2025
- 3 min read
GLM-4.6, MiniMax-M2, and Ministral-3 Now Available on FriendliAI
GLM-4.6
MiniMax-M2
Ministral-3

- December 11, 2025
- 6 min read
Why We Built a Unified Tool-Call Config Generator and Parser for Frontier Models
Unified Tool-Call Config Generator
Parser
Frontier Models

- December 2, 2025
- 2 min read
Enterprise Features Now Available on Friendli Dedicated Endpoints (Basic Plan)
Friendli Dedicated Endpoints
Basic Plan
Upgrade

- December 1, 2025
- 6 min read
FriendliAI Achieves 3× Faster Qwen3 235B Inference Compared to vLLM Infrastructure
Qwen3 235B
Benchmark
Inference