dogecat
Try itAPIPricing
Sign inGet started
One API key. Any model.

Every model.
One key.

An OpenAI-compatible endpoint that routes one key across a live model catalog. On top of the router: virtual models that put two models on hard problems, and an agentic workspace with web search and GitHub context. Your first million tokens are free.

Start building freeTry it — no signup
First-party models from $0.20/M1M free tokens on signupNo credit card required
dogecat workspace
❯why does my Next.js build die with “self is not defined”?
⧗ searching the web · Exa
⧗ reading github.com/vercel/next.js
⧗ dogecat/moa — two models proposing in parallel
✦ synthesizing the final answer
A browser-only module is evaluated during SSR. Load it dynamically with ssr disabled:
- import Chart from "react-chartjs"
+ const Chart = dynamic(() => import("react-chartjs"), { ssr: false })

More than a router.

One OpenAI-compatible endpoint, a live model catalog behind it — and the things a plain router doesn't have: virtual models, web search, GitHub context.

Any model. One endpoint.

OpenAI-compatible end to end. Change one line — your base URL — and every model in the live catalog is one API key away. Live per-model pricing at /api/v1/models.

Two models. One answer.

Call dogecat/moa like any other model id — two models answer in parallel, then a synthesis pass merges the strongest parts into a single answer that beats either alone.

Answers from today's docs

Toggle web search and the agent reads live results before it answers — current docs, changelogs, and issues instead of stale training data.

Reads your repo

Paste any GitHub link — repo, file, or directory — and the agent reads it before replying. No setup, no indexing, no waiting.

Virtual models

One model id. Two models behind it.

01

Fan out

Your task — plus any web or GitHub context — goes to two frontier models from the catalog at the same time.

02

Synthesize

An orchestrator pass reads both proposals: correcting errors, merging strengths, filling gaps.

03

Stream

One final answer, streamed live — metered cost-weighted, like any other call from your token pool.

Pricing that fits in your head.

One token pool, cost-weighted — each model draws at its own rate. Live per-model pricing at /api/v1/models.

Free
$0

1M free tokens on signup. The full workspace — dogecat/moa, web search, GitHub context.

Start free
Pay as you go
from$0.20/ 1M tokens

First-party models from $0.20/M, in and out — cheaper ones draw less. $5/mo for 100M standard tokens — $100/mo for 2.5B — plus one-time top-ups.

View API docs
Platforms
$1= 5M standard tokens

Mint credit-capped API keys for your own users. Per-key budgets, usage, and revocation — credit is standard tokens at the $0.20/M rate; models draw cost-weighted.

Platform keys docs

Your first million tokens are free.

No credit card. The full workspace — dogecat/moa, web search, GitHub context — and every model in the catalog one OpenAI-compatible call away.

Get started free
© 2026 Dogecat
TermsPrivacyDocs