UTC

DeepSeek R1 0528

DeepSeek · open weights · served by 18 providers · reasoning

deepseek/deepseek-r1-0528

Weights
Open
Released
2025-05-28
Knowledge cutoff
2024-07
Context window
66K
Deprecation dates

When each platform deprecates DeepSeek R1 0528, as LiteLLM records it. Plan the move before the date: after it, the platform may stop serving the model or stop updating it.

  • Together AIdeprecated 2026-07-29together_ai/deepseek-ai/DeepSeek-R1-0528successor: together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017
Every upcoming deprecation →
Hugging Face repository

deepseek-ai/DeepSeek-R1-0528 at commit 4236a6af53, last changed 2025-05-29

Licence
mit
Access
Open download
Library
transformers
Formats
.safetensors
  • Loading it runs code from the repository (trust_remote_code). Read that code, and pin the commit.
  • No model signature file is published with the weights.

What the Hub's scanners report

42 weight files, 0 with a scan result. No scanner reports an issue with them.

The model at this commit, its 42 weight files with their SHA-256.

Facts from the Hugging Face Hub and its file scanners (Protect AI, Cisco, Hugging Face picklescan, VirusTotal, JFrog), as of 2026-11-18. ShieldMap does not copy model cards.

Who serves it
  • Deep Infradeepseek-ai/DeepSeek-R1-0528
  • Eden AIdeepinfra/deepseek-ai/DeepSeek-R1-0528
  • Eden AItensorx/deepseek/deepseek-r1-0528
  • Hugging Facedeepseek-ai/DeepSeek-R1-0528
  • IO.NETdeepseek-ai/DeepSeek-R1-0528
  • Jiekou.AIdeepseek/deepseek-r1-0528
  • Kilo Gatewaydeepseek/deepseek-r1-0528
  • Meganovadeepseek-ai/DeepSeek-R1-0528
  • Merge Gatewaydeepseek/deepseek-r1-0528
  • NanoGPTdeepseek-ai/DeepSeek-R1-0528
  • Novita AIdeepseek/deepseek-r1-0528
  • OpenRouterdeepseek/deepseek-r1-0528
  • Qiniudeepseek-r1-0528deprecated
  • SiliconFlowdeepseek-ai/DeepSeek-R1
  • SiliconFlow (China)Pro/deepseek-ai/DeepSeek-R1
  • SiliconFlow (China)deepseek-ai/DeepSeek-R1
  • submodeldeepseek-ai/DeepSeek-R1-0528
  • TensorXdeepseek/deepseek-r1-0528deprecated
Running it yourself

Open weights are loaded and served by code that has its own advisories. These inference servers and model loaders are on ShieldMap; load weights only from the publisher's own repository, and prefer safetensors over formats that can run code.

How supply-chain attacks on models work →

Sources: models.dev (MIT) and the LiteLLM model catalogue (MIT). Deprecation dates are as each platform published them and as LiteLLM records them; check the platform before you rely on one. Data as of 2026-11-22.