Ground Truth.
AI, checked against the source.

← All topics

model-routing

Everything on Ground Truth tagged “model-routing” — 7 items.

A proxy with 49,000 stars keeps Claude Code and swaps the model News

Free Claude Code, an MIT-licensed local proxy that lets Claude Code talk to roughly 50 other model providers while preserving Anthropic's wire protocol, has passed 49,000 GitHub stars, and its per-tier routing shows exactly which layer users actually value.

NVIDIA built a 30B model for the boring half of agent work News

NVIDIA released Nemotron 3.5 Lightning, a 30-billion-parameter mixture-of-experts model that activates only 3 billion parameters per token and is aimed at the tool calls and validation steps that consume most of a long-running agent's time.

OpenRouter programming collection Tool

OpenRouter's curated collection of models for coding and agentic work, including the stealth/ox-alpha listing. Useful for A/B testing several coding models behind one API without separate accounts, and for checking a model's advertised context and modality contract before you build against it.

OpenRouter discounted models Tool

A live collection of models currently carrying provider discounts on OpenRouter. GPT-5.6 Sol from the OpenAI provider is listed at roughly half OpenAI's own promotional rate, against $5 and $30 for the same model via Azure.

OpenRouter Auto Exacto Tool

OpenRouter's provider-routing system that repeatedly evaluates provider telemetry and benchmark behavior, then deranks statistical outliers.

Multi-Head Latent Control Tool

Freezes a model and attaches two small heads that read its hidden states to decide whether to answer, use a tool, ask for information, abstain, or escalate to a stronger model. Open-sourced with matching small checkpoints; needs white-box access.

Free Claude Code Tool

MIT-licensed local proxy that lets Claude Code, Codex, OpenCode and other coding agents run against roughly 50 different providers, preserving Anthropic's wire protocol so the client never notices. Routes each internal model tier to a different upstream.