DeepSeek V4 Flash Vision Exp
DeepSeek · open weights · served by 16 providers · tool calling, reasoning, image input
deepseek/deepseek-v4-flash-vision-exp
- Weights
- Open
- Released
- 2026-08-21
- Knowledge cutoff
- Not stated
- Context window
- 1M
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp at commit 6821d6ad36, last changed 2026-09-01
- Licence
- mit
- Access
- Open download
- Library
- transformers
- Formats
- .safetensors
- No model signature file is published with the weights.
What the Hub's scanners report
11 weight files, 11 with a scan result. No scanner reports an issue with them.
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.
- AIHubMixdeepseek-v4-flash-vision-expdeprecated
- AI/ML APIdeepseek/deepseek-v4-flash-vision-exp
- AMDDeepSeek-V4-Flash-Vision-Expdeprecated
- CommandCodedeepseek/deepseek-v4-flash-vision-exp
- Deep Infradeepseek-ai/DeepSeek-V4-Flash-Vision-Exp
- Eden AIdeepseek/deepseek-v4-flash-vision-exp
- Hugging Facedeepseek-ai/DeepSeek-V4-Flash-Vision-Exp
- Kilo Gatewaydeepseek/deepseek-v4-flash-vision-exp
- DevPass (LLM Gateway)deepseek-v4-flash-vision-exp
- LLM Gatewaydeepinfra/deepseek-v4-flash-vision-exp
- NanoGPTdeepseek/deepseek-v4-flash-vision-exp
- OpenCodedeepseek-v4-flash-vision-expdeprecated
- OpenRouterdeepseek/deepseek-v4-flash-vision-exp
- OrcaRouterdeepseek/deepseek-v4-flash-vision-exp
- SiliconFlowdeepseek-ai/DeepSeek-V4-Flash-Vision-Exp
- Vercel AI Gatewaydeepseek/deepseek-v4-flash-vision-exp
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.
- vllm · 131 advisories
- transformers · 24 advisories
- keras · 20 advisories
- onnx · 17 advisories
- bentoml · 16 advisories
- github.com/ollama/ollama · 16 advisories
- torch · 13 advisories
- lmdeploy · 10 advisories
- sglang · 10 advisories
- skops · 4 advisories
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.