# I Route Every AI Agent to the Cheapest Model with Quota. Here's What Broke

> Source: <https://dev.to/galadev/i-route-every-ai-agent-to-the-cheapest-model-with-quota-heres-what-broke-3p5h>
> Published: 2026-11-18 18:01:41+00:00

**Recommendation:** Route agent tasks through a cheapest-first tier list with a 90% quota cutoff and 60-second startup-failure fallback, and escalate tiers manually rather than automatically.
More in the playbook "Controlling LLM cost": <https://wpnews.pro/playbooks/llm-cost>

I wanted coding with AI agents to be genuinely cheap, so I built a tiny Python router that sends every task to the cheapest model that still has quota left.

Within three days, a cheap model wrote a test that looped forever and ate 9 GB of RAM, another stopped halfway with "Free usage limit reached", and a third dumped 419 lines of duplicated helper functions into a script because it assumed "the grader supplies tests." 😅

Everyone is asking whether coding with AI is actually faster and cheaper. My honest answer? It's fast and nearly free, right up until a cheap model writes something that takes two hours to unwind.

So here's the router, the rules that came out of those crashes, and why it's forbidden from upgrading itself.

**TL;DR:**

The first mistake I made was tying each agent prompt to a model.

Now the role ("writer", "designer", "coder") is just a prompt with rules and skills, and **a role never names a model**. It only says what size of work it usually does.

Why does that matter? Because the moment a model is hardcoded, you can't route around outages, renamed models or an exhausted rate limit. The tier list does that for you:

```
{
  "small":  ["free-model-a", "free-model-b", "cheap-model-c"],
  "medium": ["mid-model-a", "mid-model-b"],
  "large":  ["big-model-a", "big-model-b"]
}
```

Cheapest first, more capable after. Swapping a model is a one-line change, and no prompt has to know.

When a task comes in, the router walks the requested tier and filters it:

``` python
def select_candidates(tier, tiers, allow_paid=False, forced=None):
    if forced:
        return [forced], []
    to_try, skipped = [], []
    for cand in tiers[tier]:
        if cand.get("paid") and not allow_paid:
            skipped.append((cand, "paid model not allowed"))
            continue
        if (q := quota_status(cand)):
            skipped.append((cand, f"quota: {q}"))
            continue
        to_try.append(cand)
    return to_try, skipped
```

`quota_status()` reads the CLI's local usage numbers instead of hitting a rate-limit API. If any window (rolling hours or weekly) is above **90%**, that model is out.

Why 90 and not 100? Start a big task at 96% and it tends to run dry mid-stream, leaving half-written files behind. The buffer is cheaper than the cleanup.

And yes, you can force a model by hand. The router just warns you and gets out of the way.

What about a model that gets picked and then falls over before doing anything?

AI CLIs fail at startup in creative ways: renamed models, instant 429s, free tiers that cut you off at second zero. So the router watches the first minute:

```
STARTUP_ERRORS = ("429", "model_not_found", "Free usage limit", "quota")

def is_startup_failure(code, seconds, log):
    if seconds > 60:
        return False
    if any(e.lower() in log.lower() for e in STARTUP_ERRORS):
        return True
    return code != 0
```

Fail fast, and it rolls to the next candidate in the same tier. Every run also leaves its prompt, raw log, final answer and the choice it made, so I can see *why* a model was skipped without guessing.

Did the router make everything smooth? Not even close. A few of my favourite disasters:

`model_not_found`. Lesson: only route to models you've actually run.
(If you like this kind of thing, my [previous post on running a side project with AI agents](https://dev.to/galadev/i-run-a-side-business-with-ai-agents-heres-what-broke-in-14-days-4ch) has more.)

When every small model fails, why not bump the task to a bigger one automatically?

Because **the router never decides that a task is bigger. Only I do.**

When a small task fails across the board, it's rarely the model being dumb. It's usually:

Auto-escalating just pays premium prices to retry a broken prompt. So when a tier runs out, the router exits loudly and lists why it skipped each model. Then I either fix the prompt or bump the size by hand.

The machine executes; the human owns the scope.

I don't have a dollar figure, since most of this runs on subscriptions and free tiers rather than metered APIs.

What it saved was **headroom and attention**:

The one rule I'd keep if I had to delete everything else:

**Cheapest-with-quota is the right default for writing and small scoped edits. For anything with tests, set a higher floor.**

Saving ten minutes of quota is worthless if you spend an hour reverting a cheap model's "tests".

I use this router to keep a few small data sites running on my own, like a [cheapest fuel price map for Spain](https://fuelspot.devetty.es/?utm_source=devto&utm_medium=article&utm_campaign=cheapest-model-router&utm_content=intro) and a [public tenders finder](https://licitacionesalerta.es/?utm_source=devto&utm_medium=article&utm_campaign=cheapest-model-router&utm_content=outro).

The agents are the easy part. Getting people to find and *use* the sites is the hard one. So, for anyone who's grown a side project:

I read and reply to every comment 💛

*I write these with help from AI agents.*
