Model family

Moonshot AIUpdated 2026AgentsCodeReasoning

Kimi Models

Kimi models from Moonshot AI focus on agentic coding, tool use, long-context reasoning, and workflow automation.

Best for

Agents

Use this family hub to compare Kimi variants for agents workflows, then open the detail page for deeper deployment notes.

Code

Use this family hub to compare Kimi variants for code workflows, then open the detail page for deeper deployment notes.

Reasoning

Use this family hub to compare Kimi variants for reasoning workflows, then open the detail page for deeper deployment notes.

Source box

Kimi family pages should distinguish open-weight K2 checkpoints from the hosted Kimi product/API terms.

Verified through: June 2026

Model licenses, context windows, release names, and provider terms can vary by checkpoint. Verify the exact model card before production or commercial use.

Variants

Kimi models grouped by workflow

Latest / flagship

Coding

Compare

All Kimi models in the directory

ModelTypeBest forLocal runner notesLicenseDetail
Kimi K2.6AgentsBuilders testing agentic coding, tool calling, long-context planning, and workflow automation.Server-class for full models; hosted inference is usually the most practical way to evaluate current Kimi releases.Check exact model cardOpen
Kimi K2AgentsBuilders comparing earlier Kimi releases against newer Kimi K2.6 behavior.Server-class for full weights; use hosted providers for practical evaluation.Modified MITOpen

Source box

Kimi family pages should distinguish open-weight K2 checkpoints from the hosted Kimi product/API terms.

Verified through: June 2026

Model licenses, context windows, release names, and provider terms can vary by checkpoint. Verify the exact model card before production or commercial use.