Models

One simple model name. Lowest price.

Every model has an upfront price per million tokens. Just use the model name you want, and InfinityRouter routes your request to the cheapest working provider automatically.

No models currently enabled.

Invoking Any Model via SDK

pythonPython SDK
from openai import OpenAI

client = OpenAI(
    base_url="https://infinityrouter.qd.je/v1",
    api_key="inf_live_...",
)

# 1. Claude 3.5 Sonnet (70% Cheaper)
claude_resp = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[{"role": "user", "content": "Explain raft consensus algorithm."}],
)

# 2. DeepSeek R1 (Advanced Reasoning)
reason_resp = client.chat.completions.create(
    model="deepseek-r1",
    messages=[{"role": "user", "content": "Solve this optimization puzzle step by step."}],
)

print(claude_resp.choices[0].message.content)
typescriptTypeScript / Node.js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://infinityrouter.qd.je/v1",
  apiKey: process.env.INFINITY_API_KEY,
});

async function main() {
  const completion = await client.chat.completions.create({
    model: "claude-sonnet-5",
    messages: [{ role: "user", content: "Optimize this SQL query for high concurrency." }],
  });

  console.log(completion.choices[0]?.message.content);
}

main().catch(console.error);

Canonical Stability Guarantee

Use standardized model names like claude-sonnet-5 or gpt-5. We handle provider prefixes, version mapping, and routing behind the scenes.

Start Saving TodayRead Documentation