As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/kimi-k2-thinking/

# Kimi K2 Thinking

Moonshot AI, Kimi K2 family. Status: retired. Type: reasoning model. Released: 2025-11. Training cutoff: not published.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Kimi API (discontinued) | `kimi-k2-thinking / kimi-k2-thinking-turbo` | https://api.moonshot.ai/v1 | https://platform.kimi.ai/docs/models |
| OpenRouter | `moonshotai/kimi-k2-thinking` |  | https://openrouter.ai/moonshotai/kimi-k2-thinking |
| Hugging Face |  |  | https://huggingface.co/moonshotai/Kimi-K2-Thinking |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: text
- Output: text
- Context window: 262,144 tokens
- Max output: not published
- Open weights: yes
- Licence: modified-mit

## What it has not seen

- No published training cutoff. Counted from its release (2025-11): at least 1,970 AI events since (450 major, 85 historic), as of 2026-11-13.
- Everything since October 2025: https://postcutoff.com/since/2025-10/

## What stands out

- Long tool-call chains: Interleaves reasoning with function calls and stays coherent across 200-300 sequential tool calls (vs 30-50 for earlier models, per Moonshot). Source: https://huggingface.co/moonshotai/Kimi-K2-Thinking
- Native INT4 via quantization-aware training: QAT in post-training gives a lossless ~2x speed-up at INT4 on a 1T/32B-active MoE. Source: https://huggingface.co/moonshotai/Kimi-K2-Thinking
- Heavy mode: Parallel 8-trajectory rollout with reflective aggregation used for top benchmark results (HLE, BrowseComp). Source: https://huggingface.co/moonshotai/Kimi-K2-Thinking

## Notes

kimi-k2 series (incl. K2 Thinking, K2-0905, K2-0711) discontinued on the Kimi API on 2026-05-25; Moonshot recommends kimi-k3. Still available as open weights and via third parties. Pricing not verified.

Landmark open-weight thinking agent (Nov 2025). Use for self-hosting or research; for API use kimi-k3 or kimi-k2.6.

Sources: https://huggingface.co/moonshotai/Kimi-K2-Thinking · https://platform.kimi.ai/docs/models

Model page: https://postcutoff.com/m/kimi-k2-thinking/