I'm using GPT Sol and Claude Opus for free — pi-coding-agent + OmniRoute

2026年8月25日2 次浏览来源:Dev.to阅读原文

I'm using GPT Sol and Claude Opus for free.

No credit card, no per-token bill, no "you've hit your monthly limit" email.

Two pieces of software make it happen: Pi — the coding agent that reads, writes, and runs commands in my terminal.

OmniRoute — a local gateway that sits in front of hundreds of AI providers, dozens of them free, and routes every request to the cheapest one that works.

Here's the exact setup, from install to first prompt.

What "free" means here OmniRoute ships with free-tier providers pre-wired into the model.

You don't paste an API key — a fresh install just answers.

But also reaches frontier-class models through the free routes, so I can pick them by name: Pi talks to one endpoint ().

OmniRoute handles which provider actually serves the request, and falls back automatically if one goes down or hits a rate limit.

1.

Install both The gateway boots on port ; the dashboard is at .

Quick note so you install the right thing: this is the npm (), a coding agent with read / bash / edit / write tools.

It's unrelated to the Rust project also called .

2.

Add OmniRoute as a Pi provider Pi reads its providers from .

Add an entry: — OmniRoute speaks the OpenAI protocol. — the local gateway.

Keep the . — empty is fine: OmniRoute runs keyless locally.

If you've created a key on the dashboard's Endpoints page, put it here instead.

If you already have providers in that file, just add the key next to them — don't overwrite the rest.

3.

Make it the default Edit : Now uses OmniRoute out of the box, no flags needed.

4.

Run it Switching models is one flag — no reconfiguring keys, no new accounts.

If you ever want your local Ollama model back, does it.

Two gotchas that cost me time

1.

The dashboard writes the wrong file for this Pi.

OmniRoute's built-in "Pi" integration (dashboard → CLI tools → Pi) writes .

This Pi reads .

Edit the file by hand as above and you're done — the dashboard button won't do it for this version.

2.

Bare OpenAI model names fail.

Requesting (no prefix) returns .

The free routes are namespaced — use , , or IDs like .

Why this beats juggling provider keys $0 — no card, no bill, no key management.

One endpoint — every tool and model behind .

Auto-fallback — a rate-limited or dead provider swaps out without you noticing.

One config — switching models in Pi is , not a support ticket.

Install OmniRoute, point Pi at it, and go.

Ten minutes, and GPT Sol and Claude Opus are just models you can pick.

分享