DefaultModel: Hosting only one model, the best open source model

DefaultModel, a new AI inference provider, launched with a single-model approach, hosting only the community-voted best open source model, currently GLM-5.3-flash, a 320B MoE model with 18B active parameters and 1M context, priced at $0.50 per 1M input tokens, $1.00 per 1M output tokens, and $0.15 per 1M cache tokens. The company claims 99.9% uptime, zero data retention, and U.S.-based hosting, with a challenger model replacing GLM-5.3-flash only if it wins a community vote.

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 python 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