Tag
Not Diamond released a methodology for model routing that achieves Opus-level quality while reducing agent costs by 20–80%, using a sequential decision approach to handle long-running coding agents effectively.
Releasing a methodology for evaluating model routing with interactive benchmarks that achieve Pareto-dominance over leading benchmarks, offering higher quality at lower cost.
Pro-Router introduces a token-aware progressive model routing method for efficient multimodal LLM inference, leveraging adaptive edge-cloud collaboration to improve throughput and reduce costs.
Tamarind introduces a molecular AI model router that automatically selects the best model for specific inputs based on benchmarks and input characteristics, rather than relying on average performance.
Experiential is an open-source gateway and router for AI agent workflows that enables usage-based optimization of models through a single OpenAI-compatible API.
The article argues that model choice should be boring infrastructure in AI, allowing workflows to remain stable while switching models based on tasks, and introduces Unstoppable AI as a tool built around this concept.
Fast Inference is an LLM API service that offers fast and affordable access to top open-source and closed-source models for developers, with integrations for coding agents and tools like Claude Code and Codex.
The author conducted a small experiment on LlamaIndex's extractbench benchmark, comparing Claude Opus 5 and Qwen models, finding similar performance with cost advantages and a correlation between extraction difficulty and document length.
Stripe is acquiring OpenRouter, a platform providing a unified interface for AI model routing, highlighting the rapid growth and increasing importance of model routing in the AI industry.
Google DeepMind introduces a routing method framed as a Pandora's Box problem to efficiently allocate compute by deciding when to invest in better model selection estimates, demonstrating improved performance on benchmarks like MATH, RAG, and EmbedLLM.
Harvey shares strategies for achieving world-class AI research on a limited budget through domain experts guiding synthetic data, establishing evaluation sets, collaborating with labs, and employing model routing.
This article introduces the Hermes Must-Install List, featuring plugins like the all-in-one plugin suite, Web Command Center, model-switching wizard, and skill self-evolution tools, aimed at enhancing Hermes' autonomy and productivity.
The article argues that enterprises should optimize AI intelligence spend by using appropriate-sized models and hybrid systems for different tasks, rather than defaulting to expensive frontier models for all applications.
Router by Ramp is a tool that reduces AI inference costs by up to 40% by routing requests to the lowest-cost model that meets performance needs, offering a single endpoint for multiple models.
OpenRouter, an AI model marketplace and gateway, is joining Stripe to accelerate its mission of providing neutral and efficient AI inference infrastructure, while continuing to operate independently.
This paper evaluates four open-source LLM routers using a common protocol across four benchmarks, finding that performance gains are more closely tied to model tier composition than task-specific targeting.
The article argues that token price is an inadequate cost metric for AI agents, proposing that effective cost should be measured by successful runs with validation, and discusses routing and failure strategies.
Factory.ai is recommended as an agent-native software development tool for optimizing model routing in enterprise AI tasks, enhancing accuracy and cost-efficiency.
分享一个通过TeamoRouter服务免费使用DeepSeek V4和Codex的入口，该服务提供API路由和高达90%的折扣。
The article argues that many AI agent workflows waste money by routing every task to frontier models, and suggests using cheaper model tiers for simple, structured tasks while escalating harder ones. It provides a cost comparison showing up to 75% savings with a tiered approach.