Skip to content
Alpha
  • Models
  • Rankings
  • Ori

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • EU routing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for openrouterFavicon for openrouter

Pareto Code Router

openrouter/pareto-code

Compare

The Pareto Router maintains a tiered shortlist of strong coding models, ranked by Artificial AnalysisOpens in new tab coding percentiles. Set min_coding_score between 0 and 1 on the pareto-router pluginOpens in new tab to control how strong a coder you need; higher scores select stronger (and typically more expensive) models. If you omit min_coding_score, the router defaults to the High tier.

Selecting Nitro from the variant dropdown ranks the models in your tier by measured throughput and routes each request to the fastest one, so you trade some model variety for lower latency.

Read the Pareto Router docsOpens in new tab for the full selection logic, fallback behavior, and how to customize routing. For another way to route, see the Auto Router.

Compare

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Documentation

Guides, cookbooks, blog posts, and tools for building with Pareto Code Router on OpenRouter.

  • Pareto RouterGuide

Explore more models

Free AI Models on OpenRouterCollectionAI Model RankingsRanking

Top models used by Pareto Code Router

  • High tiermin_coding_score ≥ 0.661
    Favicon for anthropic
    claude-fable-5.1
  • Medium tiermin_coding_score ≥ 0.333
    Favicon for moonshotai
    kimi-k3
    Favicon for google
    gemini-3.8-flash
    Favicon for openai
    gpt-5.6-terra
  • Low tiermin_coding_score < 0.333
    Favicon for z-ai
    glm-5.3
    Favicon for moonshotai
    kimi-k3
    Favicon for google
    gemini-3.8-flash

Frequently asked questions

The Pareto Router maintains a tiered shortlist of strong coding models, ranked by Artificial Analysis coding percentiles. Set min_coding_score between 0 and 1 on the pareto-router plugin to control how strong a coder you need; higher scores select stronger (and typically more expensive) models. If you omit min_coding_score, the router defaults to the High tier.

The Pareto Code Router documentation on OpenRouter includes the Pareto Router guide. The quickstart covers API keys and your first request, and the API reference lists every parameter.

Pareto Code Router has no fixed price of its own. Each request is billed at the price of the model that serves it, so your cost depends on which model the request is routed to.

Pareto Code Router can route to models with context windows of up to 2,000,000 tokens. The context length available to a request is that of the model that serves it.

Pareto Code Router was released on April 21, 2026.