AI Briefing#model-routing
The latest AI and developer news about #model-routing, with the original source and a short summary.
The latest AI and developer news about #model-routing, with the original source and a short summary.
The new API processes text, images, audio, video, and PDFs to return confidence scores for up to 1,000 questions in a single pass at $0.10 per 1M input tokens.
The new routers weigh eleven factors per request and handle over 2.5T tokens monthly, with Auto Code matching Claude Opus 5.5 performance at 74% lower cost.
The November 2026 report identifies four key themes: harness engineering, open-weight model adoption, multi-agent workflows, and AI factory infrastructure.
Baseten launches Grid, Sandboxes, and Loops to extend its inference platform with routing, execution, and training capabilities.
The deal values the AI model routing platform at nearly 6x its recent $1.3 billion valuation, giving Stripe control over a layer that processes over 10 trillion tokens daily.
AI21 analysis of internal traffic reveals public coding benchmarks overestimate task difficulty, leading to inefficient model routing.
Routing transplant experiments on OLMoE and DeepSeek models show that forcing morality-associated expert paths significantly alters malicious code detection accuracy, independent of the model's readable workspace.
The new middleware reduced median cost per coding task by 64% in Open SWE experiments without impacting quality.
GitHub Copilot has made Tiers of Auto available to all customers, allowing developers to select Efficiency, Balance, or Intelligence modes in VS Code, CLI, and the Copilot App to optimize model routing.
The integrated structure of general-purpose LLMs is shifting toward function-specific decoupled architectures, with low-cost inference reshaping the economics of agents.
TypeSafe AI has released 'Jev', a structured decision model that is 200x faster and 400x cheaper than LLMs.
Tailscale built Aperture, a customer-facing AI model router, leveraging Vercel AI Gateway and Sandbox.
InfraLab implemented Envoy AI Gateway, leveraging model abstraction and tiered routing to reduce LLM costs by 78%.
Experiential, an open-source AI gateway that optimizes model routing by analyzing user traffic, has been released.
Switchyard handled 93% of agent calls with a 30B model, reducing costs by 74%.
Cursor Router selects models for specific tasks based on real development data, reducing costs.
Google Cloud API Gateway dynamically routes OpenAI-compatible requests to multiple LLMs.
Manifest deprecated its LLM router based on the experience of 7,000 cloud users.
A router service has launched that reduces inference costs by running multiple models simultaneously and quickly selecting the optimal one.
Cursor launched Router, which automatically selects the optimal model for a task, cutting costs by 60%.
Cactus added a 68k-parameter probe layer to Gemma 4 E2B and unveiled a hybrid inference system that uses the model's own error detection as a signal for cloud routing.
The GLM 5.2 model is available at a 35% discount through the Novita route on AI Gateway until July 24.
Task-specific routing built by teams with deep expertise in a particular task outperforms general-purpose routers on both cost and accuracy.
Model routing in AI agent systems isn't a model-selection problem but a system optimization problem involving caching, infrastructure, and regulations.