Open source models are amazing but hosting them reliably is not. Closed source labs are reliable and low cost as they can aggregate volume mostly to their latest model. At the pace of open source development, current inference providers constantly have to host multiple models, optimize for all of them, and split their GPU resources to serve them all. We're taking a different approach. We'll only host one model based, the best open source model voted by the community, and optimize specifically for it while providing all the GPU resources to it giving you reliability of a large lab for open models.
->
Hosted in America 🇺🇸
->
Zero data retention by design
->
99.9% uptime with no degraded serving
Hugging Face ->
Parameters
320B MoE (18B active)
Context
1M
Modalities
Text, Image, Video
In/Out/Cache price
$0.50 / $1.00 / $0.15 per 1M
Chat completion standard compatible
OpenAI SDK
Vercel AI SDK
LangChain
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.defaultmodel.ai/v1",
apiKey: process.env.DEFAULTMODEL_API_KEY,
});
const completion = await client.chat.completions.create({
model: "glm-5.3-flash",
messages: [{ role: "user", content: "Explain mixture-of-experts models in one paragraph." }],
});
console.log(completion.choices[0].message.content);
0 votes
A challenger replaces GLM 5.3 Flash only if it wins. One vote per person.
One model means all our capacity serves it: 99.9% uptime, high token throughput in and out, and no degraded or quantized serving.
Latency
1.9s
Throughput
110 tps
Uptime
99.98%
Recent uptime
99.98%
Last 72 hours
72h
48h
24h
Now
Throughput