DeepSeek V3.1
DeepSeek · open weights · served by 17 providers · tool calling, reasoning
deepseek/deepseek-v3.1
- Weights
- Open
- Released
- 2025-08-21
- Knowledge cutoff
- Not stated
- Context window
- 128K
When each platform deprecates DeepSeek V3.1, as LiteLLM records it. Plan the move before the date: after it, the platform may stop serving the model or stop updating it.
- Amazon Bedrockdeprecates 2027-03-30deepseek.v3-v1:0successor: deepseek.v3.2
- Together AIdeprecated 2026-05-14together_ai/deepseek-ai/DeepSeek-V3.1successor: together_ai/deepseek-ai/DeepSeek-V4-Pro-0813
- Azure AI Foundrydeprecated 2026-07-13azure_ai/deepseek-v3.1successor: azure_ai/deepseek-v4-flash
- Basetendeprecated 2026-10-16baseten/deepseek-ai/DeepSeek-V3.1successor: baseten/deepseek-ai/DeepSeek-V4-Pro-0813
deepseek-ai/DeepSeek-V3.1 at commit c0781d039f, last changed 2025-09-05
- 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.
- Built on deepseek-ai/DeepSeek-V3.1-Base.
What the Hub's scanners report
39 weight files, 39 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.
- Abacusdeepseek/deepseek-v3.1deprecated
- Amazon Bedrockdeepseek.v3-v1:0deprecated
- Deep Infradeepseek-ai/DeepSeek-V3.1
- Hugging Facedeepseek-ai/DeepSeek-V3.1
- Jiekou.AIdeepseek/deepseek-v3.1
- Meganovadeepseek-ai/DeepSeek-V3.1
- Merge Gatewaydeepseek/deepseek-v3.1
- NanoGPTdeepseek-ai/DeepSeek-V3.1
- NanoGPTdeepseek-ai/DeepSeek-V3.1:thinking
- Qiniudeepseek-v3.1deprecated
- SiliconFlowdeepseek-ai/DeepSeek-V3.1
- submodeldeepseek-ai/DeepSeek-V3.1
- Thinking Machinesdeepseek-ai/DeepSeek-V3.1
- Together AIdeepseek-ai/DeepSeek-V3-1deprecated
- TokenGodeepseek/deepseek-v3.1
- Vercel AI Gatewaydeepseek/deepseek-v3.1
- CoreWeavedeepseek-ai/DeepSeek-V3.1
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.