The unified interfacefor every model

Better prices, better uptime, no subscriptions.

Models
433
Providers
2
Endpoints
244
Billing currency
Korean won (KRW)

What is different

One OpenAI-compatible surface

Point your base_url at `/api/v1/chat/completions` and you are done. SDKs and tool calling work unchanged.

Local-first routing

When the same model runs on a local GPU and an external provider, the local one goes first. On failure the request falls through to the next candidate.

Billed in won

No dollar conversion, no foreign payment fees. Top-ups and usage are both shown in won.

Per-request cost, in the open

Token counts and the amount deducted are in the response headers and in your activity log. Check them again with `/api/v1/generation`.

Quickstart

Issue a key, change your base_url, done.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.myip.co.kr/api/v1",
    api_key="sk-mo-v1-…",
)

response = client.chat.completions.create(
    model="google/gemma-4-26b-a4b",
    messages=[{"role": "user", "content": "안녕!"}],
)
print(response.choices[0].message.content)

Popular models

View all models
Z.ai: GLM 5.3 FlashTextImageVideo
11.95T tokens weekly
by z-aiAug 26, 20261.31M context₩132 / ₩439 · 1M
11.6T tokens weekly
by openaiJul 9, 20261.05M context₩351 / ₩2,106 · 1M
10.97T tokens weekly
by tencentAug 28, 20261.05M context₩1,464 / ₩4,389 · 1M
MiniMax: MiniMax M3TextImageVideo
6.6T tokens weekly
by minimaxJun 1, 20261.05M context₩527 / ₩2,106 · 1M
5.25T tokens weekly
by tencentJul 6, 2026262.14K context₩232 / ₩927 · 1M