UTC

DeepSeek V4 Flash 0731

DeepSeek · open weights · served by 91 providers · tool calling, reasoning

deepseek/deepseek-v4-flash-0731

Weights
Open
Released
2026-07-31
Knowledge cutoff
2025-05
Context window
1M
Deprecation dates

When each platform deprecates DeepSeek V4 Flash 0731, as LiteLLM records it. Plan the move before the date: after it, the platform may stop serving the model or stop updating it.

  • Azure AI Foundrydeprecates 2026-12-03azure_ai/DeepSeek-V4-Flash-0731successor: azure_ai/deepseek-v4.1-flash-1017
  • Together AIdeprecated 2026-10-22together_ai/deepseek-ai/DeepSeek-V4-Flash-0731successor: together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017
  • aianddeprecated 2026-10-27aiand/deepseek-ai/deepseek-v4-flashsuccessor: aiand/deepseek-ai/deepseek-v4.1-flash-1017
Every upcoming deprecation →
Hugging Face repository

deepseek-ai/DeepSeek-V4-Flash-0731 at commit 7872f01b1d, last changed 2026-08-01

Licence
mit
Access
Open download
Library
transformers
Formats
.safetensors
  • No model signature file is published with the weights.

What the Hub's scanners report

24 weight files, 24 with a scan result. No scanner reports an issue with them.

The model at this commit, its 24 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
  • Adaptiondeepseek-v4-flash
  • AIHubMixdeepseek-v4-flash-0731
  • AIHubMixdeepseek-v4-flash-0731-fast
  • Alibabadeepseek-v4-flash-0731
  • Alibaba Token Plandeepseek-v4-flash-0731
  • Alibaba Token Plan (China)deepseek-v4-flash-0731
  • AMDDeepSeek-V4-Flash
  • Arceedeepseek/deepseek-v4-flash-latestbeta
  • Basetendeepseek-ai/DeepSeek-V4-Flash-0731
  • Bothubdeepseek-v4-flash-0731
  • Boundlessdsv4
  • BytePlus ModelArkdeepseek-v4-flash-ga-260731
  • Chutesdeepseek-ai/DeepSeek-V4-Flash-0731-TEE
  • Cloudflare Workers AI@cf/deepseek-ai/deepseek-v4-flash-0731deprecated
  • Confidential AIdeepseek-ai/DeepSeek-V4-Flash-0731
  • Cortecsdeepseek-v4-flash-0731
  • Deep Infradeepseek-ai/DeepSeek-V4-Flash-0731
  • DigitalOceandeepseek-v4-flash-0731
  • Doubleworddeepseek-ai/DeepSeek-V4-Flash-0731
  • Eden AIarkanecloud/deepseek-ai/DeepSeek-V4-Flash-0731
  • Eden AIdeepinfra/deepseek-ai/DeepSeek-V4-Flash-0731
  • Eden AIflexai/DeepSeek-V4-Flash-0731
  • Eden AIflexai/DeepSeek-V4-Flash-0731@eu
  • Eden AIgreenpt/deepseek-v4-flash-0731
67 more providers

Eden AI (qwen/deepseek-v4-flash-0731), Eden AI (scaleway/deepseek-v4-flash-0731), Eden AI (sference/deepseek-ai/DeepSeek-V4-Flash-0731), Eden AI (tensorx/deepseek/deepseek-v4-flash-0731), EmpirioLabs AI (deepseek-v4-flash-0731), engy (deepseek-v4-flash-0731), GreenPT (deepseek-v4-flash-0731), Hugging Face (deepseek-ai/DeepSeek-V4-Flash-0731), Inceptron (deepseek-ai/DeepSeek-V4-Flash-0731), JoinGonka (deepseek-ai/DeepSeek-V4-Flash-0731), Kilo Gateway (deepseek/deepseek-v4-flash-0731), Klavo AI (deepseek/deepseek-v4-flash-0731), DevPass (LLM Gateway) (deepseek-v4-flash-0731), LLM Gateway (alibaba/deepseek-v4-flash-0731), LLM Gateway (baidu/deepseek-v4-flash-0731), LLM Gateway (bytedance/deepseek-v4-flash-0731), LLM Gateway (canopywave/deepseek-v4-flash-0731), LLM Gateway (deepinfra/deepseek-v4-flash-0731), LLM Gateway (flexai/deepseek-v4-flash-0731), LLM Gateway (novita/deepseek-v4-flash-0731), LLM Gateway (tencent/deepseek-v4-flash-0731), Lyceum (deepseek/deepseek-v4-flash-0731), Melious (deepseek-v4-flash-0731), Merge Gateway (deepseek/deepseek-v4-flash-0731), Merge Gateway (deepseek/deepseek-v4-flash-0731-fast), Moark (deepseek-v4-flash-0731), Morph (morph-dsv4flash), Munito AI (deepseek-ai/deepseek-v4-flash), Munito AI (EU) (deepseek-ai/deepseek-v4-flash), NanoGPT (deepseek/deepseek-v4-flash-0731), NanoGPT (deepseek/deepseek-v4-flash-0731:thinking), Novita AI (deepseek/deepseek-v4-flash-0731), Ofox (deepseek/deepseek-v4-flash-0731), OpenCode (deepseek-v4-flash), OpenCode (deepseek-v4-flash-free), OpenReason (deepseek-ai/deepseek-v4-flash-0731), OpenRouter (deepseek/deepseek-v4-flash-0731), OrcaRouter (deepseek/deepseek-v4-flash-0731), Perplexity Agent (deepseek/deepseek-v4-flash-0731), Phala (deepseek/deepseek-v4-flash-0731), Prime Inference (deepseek/deepseek-v4-flash-0731), Requesty (deepseek-v4-flash-0731), Requesty (deepseek-v4-flash-0731@eu), RunInfra (deepseek-ai/DeepSeek-V4-Flash-0731), SAGG (deepseek-ai/DeepSeek-V4-Flash-0731), Scaleway (deepseek-v4-flash-0731), SCNet Token Plan (DeepSeek-V4-Flash-0731), SiliconFlow (deepseek-ai/DeepSeek-V4-Flash-0731), Standard Compute (deepseek/deepseek-v4-flash-0731), stepping stone AG (deepseek-ai/DeepSeek-V4-Flash-0731), TeamoRouter (deepseek-v4-flash), TensorX (deepseek/deepseek-v4-flash-0731), Together AI (deepseek-ai/DeepSeek-V4-Flash-0731), Tokenify (deepseek/deepseek-v4-flash), Umans AI (umans-deepseek-v4-flash-0731), Umans AI Coding Plan (umans-deepseek-v4-flash-0731), Venice AI (deepseek-v4-flash-0731), Venice AI (deepseek-v4-flash-0731-fast), Vercel AI Gateway (deepseek/deepseek-v4-flash-0731), Vivgrid (deepseek-v4-flash), Volcengine Ark (deepseek-v4-flash-ga-260731), Vultr (deepseek-v4-flash-0731), Wafer (DeepSeek-V4-Flash-0731-Fast), Wally (deepseek-v4-flash-0731), CoreWeave (deepseek-ai/DeepSeek-V4-Flash-0731), Watt Cloud (DeepSeek-V4-Flash-0731), Zenifra (zenifra/deepseek-v4-flash-0731)

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.