OpenRouter

OpenRouter is the simplest way to call a real model from OKE: no Docker, no Python, no local weights. Set provider: "openrouter" and an API key — baseUrl resolves from the verified registry.

Quick start

import { ai } from "okengine";

export const smart = ai.model("smart", {
  provider: "openrouter",
  model: "openrouter/free",
  apiKey: process.env.OPENROUTER_API_KEY,
});

export const triage = smart.prompt("triage");

import { on, flow, http } from "okengine";

export const ask = on(
  http.post(),
  flow({ asks: ["triage"] }, async (fx, input) => {
    return await fx.ask("triage", input);
  }),
);

Router aliases

OpenRouter routers are model slugs that pick (or compose) upstream models for you. Pass the slug as model on ai.model — same as any other OpenRouter id.

Consequence: the response model field is the concrete upstream that answered — log it for auditability.

Router plugin knobs (cost_tier, allowed_models, min_coding_score, fusion panel) live on OpenRouter’s request plugins / account Routing defaults; OKE passes the model slug through the openai-compatible driver.

Free Models Router — openrouter/free

Ideal for smoke tests, demos, and learning. The router filters free models for capabilities your request needs (vision, tools, structured outputs), then picks one at random.

export const smoke = ai.model("smoke", {
  provider: "openrouter",
  model: "openrouter/free",
  apiKey: process.env.OPENROUTER_API_KEY,
});

Official guide: Free Models Router.

Auto Router — openrouter/auto

Classifies the prompt (~30 task types), ranks by community spend share over a trailing 7-day window, then applies your cost band and fallbacks.

export const smart = ai.model("smart", {
  provider: "openrouter",
  model: "openrouter/auto",
  apiKey: process.env.OPENROUTER_API_KEY,
});

Official guide: Auto Router.

Pareto Router — openrouter/pareto-code

Coding-only. You set a minimum coding score (0–1); the router maps it to a tier and picks the cheapest (or fastest with :nitro) eligible model.

export const coder = ai.model("coder", {
  provider: "openrouter",
  model: "openrouter/pareto-code",
  apiKey: process.env.OPENROUTER_API_KEY,
});

Within the tier: cheapest available (+ same-tier fallbacks on provider errors). Use session_id for multi-turn stickiness. Official guide: Pareto Router.

Fusion Router — openrouter/fusion

A panel of models answers in parallel; an analyst returns structured consensus / contradictions / gaps; your outer model writes the final answer.

export const deliberate = ai.model("deliberate", {
  provider: "openrouter",
  model: "openrouter/fusion",
  apiKey: process.env.OPENROUTER_API_KEY,
});

Official guide: Fusion Router.

Body Builder — openrouter/bodybuilder

Describe a multi-model job in natural language. The response is JSON { requests: [...] } — generate is free; you execute each body yourself. Useful for A/B checks, not a single fx.ask answer.

export const builder = ai.model("builder", {
  provider: "openrouter",
  model: "openrouter/bodybuilder",
  apiKey: process.env.OPENROUTER_API_KEY,
});

Official guide: Body Builder.

Latest resolution — ~author/family-latest

Stable family alias that always retargets to the newest visible model in that family. Response model reports the concrete slug.

export const opus = ai.model("opus", {
  provider: "openrouter",
  model: "~anthropic/claude-opus-latest",
  apiKey: process.env.OPENROUTER_API_KEY,
});

Official guide: Latest Model Resolution.

Multi-provider projects

export const viaOr = ai.model("via-or", {
  provider: "openrouter",
  model: "openrouter/free",
  apiKey: process.env.OPENROUTER_API_KEY,
});

export const viaGroq = ai.model("via-groq", {
  provider: "groq",
  model: "llama-3.1-8b-instant",
  apiKey: process.env.GROQ_API_KEY,
});

Each binding keeps its own apiKey and auto-resolved baseUrl. No shared process-wide token.

Troubleshooting

Learn more

• Models — verified providers, limited compatibility, BYO /v1
• AI — prompts and fx.ask
• OpenRouter routers — Auto, Free, Pareto, Fusion, Body Builder, Latest

Any OpenAI-compatible /v1 endpoint works via custom baseUrl / OKE_AI_URL on an openai-compatible binding — see Models.

Next