D.Run (China)

$10 off Synthetic - fastest OpenCode provider$10 off Synthetic - the fastest Kimi K2.6 and GLM 5.1 provider

Provider details

Learn more about this provider, then browse the models currently listed under it.

drundrun

X LinkedIn

Provider docs

Latest news about D.Run (China)

No articles yet. Fetch the latest news to show it here.

Recent tweets and retweets from D.Run (China)

May 6, 2026, 5:54 AMUTC

vLLM v0.20.1 is now available. During this release cycle, DaoCloud collaborated deeply with community partners to deliver over 10 stability fixes and performance optimizations for DeepSeek V4, helping DeepSeek V4 run more stably and faster on vLLM. @vllm_project

Mar 24, 2026, 9:00 AMUTC

Three core AI inference cluster challenges: GPU topology, scheduling, cost validation. 🎤DaoCloud's Weizhou Lan presents topology discovery for Kueue scheduling, using Kwok virtual nodes for cost-free validation to boost GPU and cluster efficiency.

Mar 24, 2026, 6:34 AMUTC

Growing AI workloads such as LLMs make cache-aware scheduling and routing critical to GPU efficiency. 🎤Kay Yan (DaoCloud) collaborates with Red Hat & IBM to resolve K8s KV-Cache fragmentation, sharing high-performance LLM inference best practices.

Mar 23, 2026, 7:00 AMUTC

📢KubeEdge has become the preferred platform for Kubernetes edge scaling! 🎤DaoCloud's Hongbing Zhang will team up with Huawei and VMware experts to share edge workload management architecture, multi-domain cases, and the latest technical updates and community trends.

Mar 23, 2026, 6:02 AMUTC

📊How to achieve granular bandwidth management？ 🎤 Weizhou Lan, Senior Technical Director of DaoCloud, will showcase a lightweight cluster solution using Cilium CNI + Spiderpool for tenant-level ingress bandwidth management in Kubernetes without extra external complexity.

Recent tweets and retweets from D.Run (China)

About D.Run (China)

What they do

D.Run is a GPU cloud and AI model platform that offers hosted training, fine-tuning, and inference services through DaoCloud's enterprise infrastructure.

How they were founded

D.Run is part of DaoCloud, a cloud-native company founded in 2014 that later expanded into AI and GPU cloud offerings.

Sources

These links anchor the profile to public company pages, docs, and reference material.

d.run

en.d.run

daocloud.io

Quick Info

Organization: DaoCloud
Headquarters: Shanghai, China
SDK package: @ai-sdk/openai-compatible
Synced at: Apr 22, 2026

Models served

3 models available through D.Run (China)

These model results are sorted newest first so you can quickly see the latest options from this provider.

Quick tip: use the global shortcut Ctrl+K or Cmd+K to search from anywhere.

D.Run (China)minimax

MiniMax M2.5

public/minimax-m25D.Run (China)Released Mar 1, 2025204,800 token context windowIn $0.29 · Out $1.16

Input

Output

D.Run (China)deepseek-thinking

DeepSeek R1

public/deepseek-r1D.Run (China)Released Jan 20, 2025131,072 token context windowIn $0.55 · Out $2.20

Input

Output

D.Run (China)deepseek

DeepSeek V3

public/deepseek-v3D.Run (China)Released Dec 26, 2024131,072 token context windowIn $0.28 · Out $1.10

Input

Output