Kimi K2.7 Code HighSpeed
Moonshot AI · open weights · served by 68 providers · tool calling, reasoning, image input, video input
moonshotai/kimi-k2.7-code
- Weights
- Open
- Released
- 2026-06-12
- Knowledge cutoff
- 2025-01
- Context window
- 262K
When each platform deprecates Kimi K2.7 Code 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 2027-04-16azure_ai/kimi-k2.7-codesuccessor: azure_ai/kimi-k3.1-pro
- Together AIdeprecated 2026-08-27together_ai/moonshotai/Kimi-K2.7-Codesuccessor: together_ai/moonshotai/Kimi-K3.1-Pro
- Basetendeprecated 2026-10-16baseten/moonshotai/Kimi-K2.7-Codesuccessor: baseten/moonshotai/Kimi-K3.1-Pro
- aianddeprecated 2026-10-27aiand/moonshotai/kimi-k2.7-codesuccessor: aiand/moonshotai/kimi-k3
moonshotai/Kimi-K2.7-Code at commit 74797c9c62, last changed 2026-06-15
- Licence
- modified-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
33 weight files, 33 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-k2.7-code
- Abacusmoonshotai/Kimi-K2.7-Code
- AIHubMixkimi-k2.7-code
- Alibaba Token Plankimi-k2.7-code
- Alibaba Token Plan (China)kimi-k2.7-code
- Azurekimi-k2.7-code
- Azure Cognitive Serviceskimi-k2.7-code
- ClinePasscline-pass/kimi-k2.7-codedeprecated
- Cloudflare Workers AI@cf/moonshotai/kimi-k2.7-codedeprecated
- CommandCodemoonshotai/Kimi-K2.7-Code
- Cortecskimi-k2.7-code
- CrossModelmoonshot/kimi-k2.7-code
- Databricksdatabricks-kimi-k2-7-codedeprecated
- Deep Inframoonshotai/Kimi-K2.7-Codedeprecated
- DotHooshkimi-k2.7-code
- Eden AImoonshot/kimi-k2.7-code
- EmpirioLabs AIkimi-k2-7-code
- GitHub Copilotkimi-k2.7-codedeprecated
- GreenPTkimi-k2.7-code
- HPC-AImoonshotai/kimi-k2.7-code
- Hugging Facemoonshotai/Kimi-K2.7-Code
- Inceptronmoonshotai/Kimi-K2.7-Code
- Inference APIsmoonshotai/Kimi-K2.7-Code
- IteraComputemoonshotai/kimi-k2.7-code
44 more providers
Jalapeno Cloud (Kimi-K2.7-Code), Kenari (kimi-k2-7-code), Kilo Gateway (moonshotai/kimi-k2.7-code), DevPass (LLM Gateway) (kimi-k2.7-code), LLM Gateway (alibaba/kimi-k2.7-code), LLM Gateway (moonshot/kimi-k2.7-code), LLM Gateway (novita/kimi-k2.7-code), LLM Gateway (scx-ai-gp/kimi-k2.7-code), LLM Gateway (tencent/kimi-k2.7-code), Lyceum (moonshotai/kimi-k2.7-code), Melious (kimi-k2.7-code), Merge Gateway (moonshot/kimi-k2.7-code), Moneo (kimi-k2.7-code:web), Moonshot AI (kimi-k2.7-code), Moonshot AI (kimi-k2.7-code-highspeed), Moonshot AI (China) (kimi-k2.7-code), Moonshot AI (China) (kimi-k2.7-code-highspeed), NanoGPT (moonshotai/kimi-k2.7-code), Novita AI (moonshotai/kimi-k2.7-code), Ofox (moonshotai/kimi-k2.7-code), Ollama Cloud (kimi-k2.7-code), OpenCode (kimi-k2.7-code), OpenCode Go (kimi-k2.7-code), OpenReason (moonshotai/kimi-k2.7-code), OpenRouter (moonshotai/kimi-k2.7-code), OrcaRouter (kimi/kimi-k2.7-code), Perplexity Agent (moonshot-ai/kimi-k2.7-code), Requesty (kimi-k2.7-code), Requesty (kimi-k2.7-code@eu), routing.run (kimi-k2.7-code), routing.run (kimi-k2.7-code-nitro), SCNet Token Plan (Kimi-K2.7-Code), SCX.ai (Kimi-K2.7-Code), SiliconFlow (moonshotai/Kimi-K2.7-Code), Tencent Token Plan (kimi-k2.7-code), TensorX (moonshotai/kimi-k2.7-code), Venice AI (kimi-k2-7-code), Vercel AI Gateway (moonshotai/kimi-k2.7-code), Volcengine Ark Coding Plan (kimi-k2.7-code), CoreWeave (moonshotai/Kimi-K2.7-Code), Watt Cloud (Kimi-K2.7-Code), Zenifra (zenifra/kimi-k2.7-code), ZenMux (moonshotai/kimi-k2.7-code), ZenMux (moonshotai/kimi-k2.7-code-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.