Access leading AI models through a unified OpenAI-compatible inference API. Fast, reliable, and built for developers.
Everything you need to ship reliable AI features — from routing to billing — behind a single, predictable API.
One endpoint to access multiple frontier AI models. Switch models with a single parameter — no SDK changes.
Optimized routing for low-latency responses. Smart failover keeps your requests fast and resilient.
Works instantly with existing SDKs. Change the base URL and ship — no rewrites, no lock-in.
Enterprise-grade API key management, per-key rate limits, and encrypted credentials. Your data stays yours.
10 production-ready models from leading providers — all behind one API key, billed per token.
If you've used the OpenAI SDK, you already know OneRouter. Point your client at our base URL and you're done.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://onerouter.id/v1",
apiKey: process.env.ONEROUTER_API_KEY,
});
const res = await client.chat.completions.create({
model: "glm-5.2",
messages: [
{ role: "user", content: "Hello!" }
],
});
console.log(res.choices[0].message.content);Pay only for the tokens you use. No subscriptions. No hidden fees.
| Model | Provider | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
GLM-5.2 glm-5.2 | GLM | 1M | Rp1.400 | Rp3.000 | Live |
DeepSeek V4 Pro deepseek-v4-pro | DeepSeek | 1M | Rp2.500 | Rp3.500 | Live |
Qwen 7 Plus qwen3.7-plus | Alibaba | 200K | Rp2.000 | Rp6.000 | Live |
DeepSeek V4 Flash deepseek-v4-flash | DeepSeek | 1M | Rp2.300 | Rp2.600 | Live |
GLM 5.1 glm-5.1 | GLM | 200K | Rp2.300 | Rp3.500 | Live |
GLM 5.2 Fast glm-5.2-fast | GLM | 1M | Rp3.500 | Rp7.000 | Live |
Qwen3 Coder Next qwen3-coder-next | Alibaba | 200K | Rp2.000 | Rp4.000 | Live |
MiniMax M3 minimax-m3 | MiniMax | 1M | Rp1.200 | Rp2.000 | Live |
Kimi K2.7 Code kimi-k2.7-code | Moonshot AI | 250K | Rp3.500 | Rp5.500 | Live |
Kimi K2.7 Code Fast kimi-k2.7-code-fast | Moonshot AI | 250K | Rp3.000 | Rp7.000 | Live |
Ship AI features without managing multiple providers.
A clean, documented API that just works.
Benchmark models side-by-side from one interface.
Production-grade routing, observability, and control.
Get an API key in minutes. One endpoint, every model, billed per token.