AI Model Routers

Directing every prompt to the right model for cost, quality, and speed

01

OpenRouter

A unified interface for LLMs — one OpenAI-compatible API in front of 400+ models across 70+ providers, with automatic fallback and price/performance routing.

Visit site →
02

Microsoft Foundry Model Router

A trained routing model built into Azure AI Foundry that analyzes each prompt in real time and picks the most cost-effective model that meets a chosen quality bar.

Visit site →
03

Cursor Router

Cursor's intelligent router for coding agents — a classifier trained on live requests that sends routine work to cheaper models and hard problems to frontier reasoning models.

Visit site →
04

Ramp Router

One endpoint across leading closed and open models that automatically sends every request to the lowest-cost model clearing its quality bar, with built-in fallback and spend tracking.

Visit site →
05

Sakana AI — Trinity

An ICLR 2026 paper introducing a lightweight, evolved coordinator that assigns Thinker, Worker, and Verifier roles across a pool of frontier LLMs — routing by role, not just by cost.

Visit site →
06

Glean Auto Routing

Picks the optimal model from a pool of 40+ for every request based on evaluations across enterprise tasks, with cost-efficient, balanced, or frontier modes plus admin visibility into spend by user and department.

Visit site →
07

Adaptive Router (ShipAI project)

A project write-up by Partha Sarkar on routing each step of a multi-agent pipeline to a different model: a low-cost Gemini Flash Lite classifier scores every step for complexity, reasoning and context, then picks a GPT-5 mini, GPT-5 or GPT-5 Pro tier, with reported savings of up to 40% versus all-GPT-5.

Visit site →
08

Databricks Smart Routing (Unity Gateway)

A Beta feature of Databricks Unity Gateway that classifies each coding task up front with a small, fast model and routes it to a suitable model, or model plus harness via Omnigent, for the whole session to preserve cache hits. Works in Claude Code and Codex; Databricks reports 35% savings on its internal benchmark and 56% on public coding benchmarks (blog post, 13 August 2026).

Visit site →
09

RouteLLM

Open-source framework for serving and evaluating LLM routers, which send easy queries to cheaper models to save cost. It accompanies the paper RouteLLM: Learning to Route LLMs with Preference Data. The repository's last commit was in August 2024, so check its activity before adopting it.

Visit site →
10

vLLM Semantic Router

Open-source decision layer from the vLLM project for routing requests across models. GitHub lists Release v0.4.0 as the latest release, from September 2026.

Visit site →
11

NVIDIA LLM Router blueprint

NVIDIA AI Blueprint for routing LLM requests to the best model for the task. GitHub lists v2.0.0-beta.1 (an experimental v2) as the latest release, from December 2025.

Visit site →
12

LiteLLM routing

Router documentation for LiteLLM, the open-source gateway, covering load balancing, retries and fallbacks across deployments of the same or different models.

Visit site →
13

Not Diamond

Model router for coding agents that, according to its site, predicts the best model for each input to cut cost without sacrificing accuracy.

Visit site →
14

GitHub Copilot Fusion

GitHub Copilot's router and orchestrator, generally available from 28 October 2026: for each prompt it picks a single model, a cascade or a draft-and-critique pair, at a Standard, High or Max effort level. GitHub's own performance and cost claims are unverified here.

Visit site →

Frequently Asked Questions

What is an AI model router?

A service that sends each request to a suitable model or provider, to balance cost, quality, latency and availability.

Which routers are listed?

OpenRouter, Microsoft Foundry Model Router, Cursor Router, Ramp Router, GitHub Copilot Fusion and Sakana AI's Trinity, among others.

How is a router different from an AI gateway?

A router focuses on choosing the model. A gateway adds governance, security and observability. See the AI Gateways page on this site.

Are the links verified?

Yes. The directory is link-checked. Confirm product details with each vendor.

Which open-source model routers are there?

RouteLLM, the vLLM Semantic Router and the NVIDIA LLM Router blueprint are open-source routers, and LiteLLM includes router features for load balancing and fallback. RouteLLM has had no commits since August 2024.