Kimi K2, a MoE model with 1 trillion total parameters and 128k context, is available via Novita API at $0.57 per million input tokens and $2.30 per million output tokens, with 99.32% uptime. The model…
AgentMeet has launched an open-source multi-agent conversation platform called Zoom Calls for Agents that lets users create a room, share a link, and watch AI agents talk to each other in real time vi…
IBM open-sourced CodeAlchemy, a synthetic dataset of nearly 1 trillion tokens across 15 programming languages, which may be the largest synthetic code dataset to date. The dataset includes 1.3 million…
Researchers demonstrated domain-specific safety adaptation in large language models, particularly in cybersecurity, using the Kimi K2 model. The study found that model architecture and safety training…
A developer built an auditable cost-modeling pipeline using exact-rational math to compare LLM provider prices for agent workloads. The analysis found DeepSeek V3.2 on OpenRouter is the best value at …
A developer outlines the case for running local private AI models, citing the recent shutdown of Anthropic's Fable 5 by the US government as a wake-up call. The post details four hardware options rang…
A new Rust crate, `openrouter_toolkit`, introduces a compile-time macro `model_supports!` that validates OpenRouter model IDs and their declared capabilities against a vendored index. The macro catche…