Kimi K3.1 Pro Highspeed
Moonshot AI · open weights · served by 86 providers · tool calling, reasoning, image input, video input
moonshotai/kimi-k3.1-pro
- Weights
- Open
- Released
- 2026-10-23
- Knowledge cutoff
- Not stated
- Context window
- 1.048576M
When each platform deprecates Kimi K3.1 Pro Highspeed, 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 2027-11-04azure_ai/kimi-k3.1-prosuccessor: azure_ai/FW-Kimi-K3
moonshotai/Kimi-K3.1-Pro at commit d9e99b0792, last changed 2026-11-05
- Licence
- kimi-k3.1-pro
- 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
38 weight files, 38 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.
- 302.AIkimi-k3.1-pro
- AbliteratedLLMkimi-k3.1-pro
- Adzuki AIkimi-k3.1-pro
- ai&moonshotai/kimi-k3.1-pro
- Amazon Bedrockglobal.moonshotai.kimi-k3.1
- Amazon Bedrockus.moonshotai.kimi-k3.1
- Basetenmoonshotai/Kimi-K3.1-Pro
- ClinePasscline-pass/kimi-k3.1-pro
- Cloudflare AI Gatewaymoonshotai/kimi-k3.1-pro
- CommandCodemoonshotai/Kimi-K3.1-Pro
- Cortecskimi-k3.1-pro
- CrossModelmoonshot/kimi-k3.1-pro
- Deep Inframoonshotai/Kimi-K3.1-Pro
- DigitalOceankimi-k3.1-pro
- DotHooshkimi-k3.1-pro
- Doublewordmoonshotai/Kimi-K3.1-Pro
- Eden AImoonshot/kimi-k3.1-pro
- EmpirioLabs AIkimi-k3-1-pro
- engykimi-k3.1-pro
- Fireworks AIaccounts/fireworks/models/kimi-k3p1-pro
- Hugging Facemoonshotai/Kimi-K3.1-Pro
- Charm Hyperkimi-k3.1-pro
- Inferriskimi-k3.1-pro
- JZSTOKENkimi-k3.1-pro
62 more providers
Keln (moonshotai/kimi-k3.1-pro), Kenari (kimi-k3-1-pro), Kilo Gateway (moonshotai/kimi-k3.1-pro), Kimi For Coding (kimi.com) (k3.1-pro), Kimi For Coding (kimi.com) (k3.1-pro-highspeed), Kimi For Coding (kimi.ai) (k3.1-pro), Kimi For Coding (kimi.ai) (k3.1-pro-highspeed), Liquid Inference (kimi-k3.1-pro), DevPass (LLM Gateway) (kimi-k3.1-pro), LLM Gateway (alibaba/kimi-k3.1-pro), LLM Gateway (canopywave/kimi-k3.1-pro), LLM Gateway (fireworks/kimi-k3.1-pro), LLM Gateway (inference.net/kimi-k3.1-pro), LLM Gateway (moonshot/kimi-k3.1-pro), LLM Gateway (runpod/kimi-k3.1-pro), LLM Gateway (runware/kimi-k3.1-pro), LLM Gateway (scx-ai-gp/kimi-k3.1-pro), LLM Gateway (together-ai/kimi-k3.1-pro), Logits (moonshotai/kimi-k3.1-pro), Lyceum (moonshotai/kimi-k3.1-pro), Merge Gateway (moonshot/kimi-k3.1-pro), Moonshot AI (kimi-k3.1-pro), Moonshot AI (kimi-k3.1-pro-highspeed), Moonshot AI (China) (kimi-k3.1-pro), Moonshot AI (China) (kimi-k3.1-pro-highspeed), Morph (morph-kimik31), NaN (kimi-k3.1-pro), NanoGPT (TEE/kimi-k3.1-pro), NanoGPT (moonshotai/kimi-k3.1-pro), NEAR AI Cloud (moonshotai/kimi-k3.1-pro), Nebius Token Factory (moonshotai/Kimi-K3.1-Pro), Neuralwatt (kimi-k3.1-pro), Neuralwatt (kimi-k3.1-pro-flex), Neuralwatt (nw-large), Neuralwatt (nw-large-flex), Novita AI (moonshotai/kimi-k3.1-pro), Novita AI (moonshotai/kimi-k3.1-pro-highspeed), Ofox (moonshotai/kimi-k3.1-pro), Ollama Cloud (kimi-k3.1-pro), OpenCode Go (kimi-k3.1-pro), OpenRouter (moonshotai/kimi-k3.1-pro), Prime Inference (moonshotai/kimi-k3.1-pro), ProxyStacks Relay (kimi-k3.1-pro), Requesty (kimi-k3.1-pro), Requesty (kimi-k3.1-pro-highspeed), Requesty (kimi-k3.1-pro@eu), SCX.ai (Kimi-K3.1-Pro), Synthetic (hf:moonshotai/Kimi-K3.1-Pro), TeamoRouter (kimi-k3.1-pro), Tinfoil (kimi-k3-1-pro), Together AI (moonshotai/Kimi-K3.1-Pro), Umans AI (umans-kimi-k3), Umans AI (umans-kimi-k3.1-pro), Umans AI Coding Plan (umans-kimi-k3), Umans AI Coding Plan (umans-kimi-k3.1-pro), Venice AI (kimi-k3-1-pro), Vercel AI Gateway (moonshotai/kimi-k3.1-pro), Verda (kimi-k3-1-pro), Volcengine Ark Coding Plan (kimi-k3.1-pro), Wafer (Kimi-K3.1-Pro), Wallaby (moonshotai/kimi-k3.1-pro), Wallaby (moonshotai/kimi-k3.1-pro-highspeed)
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.