kimi-k2-thinking:cloud

Upstream reference: Kimi K2 Thinking

Publisher: Moonshot AI

This release is a thinking-oriented Kimi K2 derivative designed to interleave generated reasoning with function calls.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Total parameters

1 trillion Source

Active parameters

32 billion Source

Published context

256K tokens, publisher notation Source

Published checkpoint design

Native INT4 quantization Source

Upstream license metadata

Modified MIT; review linked terms Source

Publisher-described uses

• Text reasoning and multi-step tool workflows described by Moonshot AI. Source

Reference limitations

• Tool execution and access remain responsibilities of the surrounding application. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

• Kimi K2 Thinking official documentation — Moonshot AI. Checked 2026-11-02.

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• Moonshot AI — official site
• Ollama
• Hugging Face
• Official model announcement / documentation

Where kimi-k2-thinking:cloud comes from

Named in 3 observation pages

• 31 cloud models × 3 wrappers on the same audit · V1
• Academic observation — 32 cloud models × Cline and Pi · V1
• Cloud Models — three-judge autoresearch observation set · V1