OrcaRouter: Free

orcarouter/free
FREE
Text in · Text out

One endpoint for the free tier — routed by difficulty across your workspace's free models.

Overview

One endpoint for the free tier. Instead of picking a specific -free alias yourself, call orcarouter/free and it routes each request by difficulty across your workspace's free models — never touching your wallet, with free use capped by request rate rather than a fixed number of calls.

Use these from your own routers
Turn on “Use my free models first” on any router to reach for these free models before paid ones — within the same difficulty tier.

How it works

1

Classify by difficulty

Each request is scored on prompt length, code density, tools and reasoning cues — the same signal our adaptive router uses.

2

Route to a free model

Mundane prompts go to the light free tier; hard ones to the stronger free tier — drawn from your workspace’s free models.

3

Serve it for free

Model usage costs nothing — both tiers are priced at $0, so it makes no difference which one serves the request.

Limits

Free access is limited by request rate, not by a balance — the model usage itself costs nothing, and the allowance never runs out.

Per account

Every workspace gets a request-rate allowance. It grows with what you have paid for over the account’s lifetime, so topping up raises the free limits too.

Per model

Individual free models can carry their own tighter rate, so a heavily-loaded one throttles without affecting the rest.

How free-tier limits work

Free models it routes to

Code samples

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="orcarouter/free",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

FAQ

What is orcarouter/free?
A curated router over the free-tier models included with every workspace. It classifies each request by difficulty and sends easy prompts to the light free model, hard ones to the stronger free model — one endpoint instead of picking an alias yourself.
How is it billed?
It never touches your wallet balance. The models it routes to are priced at zero, so a call through orcarouter/free costs nothing regardless of which tier serves it.
How is free usage limited?
By request rate, not by a fixed pot of calls — nothing runs out. Every workspace can keep calling the free tier indefinitely, as long as it stays within the rate limits.
What happens when I hit the limit?
Exceeding the request rate returns HTTP 429 with a Retry-After header telling you how long to wait — access restores itself, no action needed. A single prompt above the tier's size limit is refused with the same status but will not pass on retry; shorten it instead. Topping up your balance raises the free-tier limits.