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.

Active Models
9
Model Families
7
Vision capable
8
Tool/Function calling
9
Rates starting from
$0.00
All 9 models, by canonical ID
Model & FamilyContext WindowMax OutputCapabilitiesInput / 1M tokensOutput / 1M tokens
BlackNightmare Xblacknightmare-x1M128,000Tools · Vision · Stream$25.85$69.50
Infinity 6.1 Solinfinity-6.1-sol1M128,000Tools · Vision · Stream$3.00$15.00
Infinity Camel Flashinfinity-camel-flash1M128,000Tools · Vision · Stream$1.00$5.00
Infinity Foreverinfinity-forever250K128,000Tools · Stream$0.00$0.00
Infinity GPTKiller Flashinfinity-gptkiller-flash200K128,000Tools · Vision · Stream$0.20$0.50
Infinity Mimo Flashinfinity-mimo-flash200K128,000Tools · Vision · Stream$0.50$0.50
Infinity PoPoinfinity-popo200K65,000Tools · Vision · Stream$1.00$4.00
Infinity PoPo Flashinfinity-popo-flash200K128,000Tools · Vision · Stream$0.10$0.50
Infinity Step Previewinfinity-step-preview1M128,000Tools · Vision · Stream$2.00$8.00

Invoking Any Model via SDK

pythonPython SDK
from openai import OpenAI

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

completion = client.chat.completions.create(
    model="blacknightmare-x",
    messages=[{"role": "user", "content": "Explain raft consensus algorithm."}],
)

print(completion.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: "blacknightmare-x",
    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