OpenAI-compatible inference · 10 models live

One API.
The World's Best
AI Models.

Access leading AI models through a unified OpenAI-compatible inference API. Fast, reliable, and built for developers.

No credit card requiredPay per tokenDrop-in OpenAI replacement
onerouter — chatlive
latency
tokens
status
Frontier models, one gateway
GLMDeepSeekAlibaba QwenMoonshot AIMiniMax
Developer Infrastructure

Infrastructure for production AI

Everything you need to ship reliable AI features — from routing to billing — behind a single, predictable API.

Unified API

One endpoint to access multiple frontier AI models. Switch models with a single parameter — no SDK changes.

Fast Inference

Optimized routing for low-latency responses. Smart failover keeps your requests fast and resilient.

OpenAI Compatible

Works instantly with existing SDKs. Change the base URL and ship — no rewrites, no lock-in.

Secure & Reliable

Enterprise-grade API key management, per-key rate limits, and encrypted credentials. Your data stays yours.

Model Catalog

Frontier models, ready to call

10 production-ready models from leading providers — all behind one API key, billed per token.

Browse all models →

GLM-5.2

GLM
Live
Context
1M
Capability
General Intelligence
glm-5.2Try

DeepSeek V4 Pro

DeepSeek
Live
Context
1M
Capability
Reasoning
deepseek-v4-proTry

Qwen 7 Plus

Alibaba
Live
Context
200K
Capability
General Intelligence
qwen3.7-plusTry

DeepSeek V4 Flash

DeepSeek
Live
Context
1M
Capability
Low Latency
deepseek-v4-flashTry

GLM 5.1

GLM
Live
Context
200K
Capability
General Intelligence
glm-5.1Try

GLM 5.2 Fast

GLM
Live
Context
1M
Capability
Low Latency
glm-5.2-fastTry
Performance

Built for scale and speed

0+
AI Models
0M+
Maximum Context
<0ms
Fast Response
0.0%
Reliability
Developer Experience

From zero to inference in minutes

If you've used the OpenAI SDK, you already know OneRouter. Point your client at our base URL and you're done.

Works with your stack
OpenAI SDK
Drop-in base URL swap
Python
Official SDK
Node.js
Official SDK
LangChain
LLM provider
Vercel AI SDK
Stream & generate
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);
javascriptonerouter.id/v1
Pricing

Simple usage-based pricing

Pay only for the tokens you use. No subscriptions. No hidden fees.

ModelProviderContextInput / 1MOutput / 1MStatus
GLM-5.2
glm-5.2
GLM1MRp1.400Rp3.000Live
DeepSeek V4 Pro
deepseek-v4-pro
DeepSeek1MRp2.500Rp3.500Live
Qwen 7 Plus
qwen3.7-plus
Alibaba200KRp2.000Rp6.000Live
DeepSeek V4 Flash
deepseek-v4-flash
DeepSeek1MRp2.300Rp2.600Live
GLM 5.1
glm-5.1
GLM200KRp2.300Rp3.500Live
GLM 5.2 Fast
glm-5.2-fast
GLM1MRp3.500Rp7.000Live
Qwen3 Coder Next
qwen3-coder-next
Alibaba200KRp2.000Rp4.000Live
MiniMax M3
minimax-m3
MiniMax1MRp1.200Rp2.000Live
Kimi K2.7 Code
kimi-k2.7-code
Moonshot AI250KRp3.500Rp5.500Live
Kimi K2.7 Code Fast
kimi-k2.7-code-fast
Moonshot AI250KRp3.000Rp7.000Live
Prices per 1 million tokens. You only pay for tokens consumed — no subscriptions, no hidden fees.
Trusted by builders

Built for developers building the future of AI applications

Startups

Ship AI features without managing multiple providers.

Developers

A clean, documented API that just works.

Researchers

Benchmark models side-by-side from one interface.

AI Engineers

Production-grade routing, observability, and control.

Ship AI features faster

Get an API key in minutes. One endpoint, every model, billed per token.