$ cat wiki/models/kimi-k3.md
Kimi K3
modelupdated 2026-07-27created 2026-07-20
Compared with
- Qwen 3.8 27B
- DeepSeek V4-Pro-0813
- Gemini 3.7 Flash
- Muse Glimmer
- Grok 4.6
- Claude Opus 5
- Laguna S 2.1
- Inkling
- GPT-5.6 Sol
- LongCat-2.0
- GLM-5.2
- MiniMax M3
- Muse Spark 1.2
- Qwen 3.8 Max
- DeepSeek V4-Flash
- Gemini 3.5 Flash-Lite
- Gemini 3.6 Flash
- DeepSeek V4
- Grok 4.5
- Claude Sonnet 5
- Claude Fable 5
- Claude Opus 4.8
- Gemini 3.5 Flash
- Grok Build
- Claude Opus 4.7
- Muse Spark
Spec
| Attribute | Value |
|---|---|
| Developer | Moonshot AI |
| Released | 2026-07-16 |
| Announced | 2026-07-16 |
| Context window | 1M tokens |
| Pricing | $0.30/M cache-hit input · $3.00/M cache-miss input · $15.00/M output |
| License | Modified MIT (commercial use permitted; weights publicly downloadable) |
| Availability | Kimi Code, Kimi app, Kimi API; weights on Hugging Face (moonshot-ai/kimi-k3, released 2026-07-27) |
Release Date
July 16, 2026.
Benchmarks
- Frontend Code Arena: beats Anthropic Fable 5 (human-preference Elo) — Moonshot's reported benchmark
- Positioned as strongest open-weight model at launch for agentic coding
Use Cases
- Long-horizon agentic coding (K3 Swarm Max variant)
- Chat and general assistant tasks (K3 Max variant)
- Parallel agent workloads (K3 Swarm Max)
Compared To
| Model | Params | Context | Open? |
|---|---|---|---|
| Kimi K3 | ~2.8T MoE | 1M | Yes (Modified MIT, released July 27) |
| Qwen 3.8 Max | ~2.4T MoE | unknown | Planned |
| GLM-5.2 | 744B MoE | 1M | Yes (MIT) |
| Claude Fable 5 | unknown | 200K | No |
| MiniMax M3 | 428B MoE | 1M | Yes |
Architecture
- Kimi Delta Attention (KDA): hybrid linear attention mechanism enabling efficient 1M-token processing
- Attention Residuals: enhances long-context coherence
- 896 experts; ~16 active per token (~1.8% activation ratio)
- Native visual understanding
Variants
- Kimi K3 Max — chat and agent tasks
- Kimi K3 Swarm Max — large-scale parallel agent processing
Sources
- Kimi API docs: quickstart
- Simon Willison analysis: kimi-k3
- Tom's Hardware: largest open-weight
Referenced by
DeepSeek V4-Pro-0813DiffusionGemmaGemini 3.6 FlashInklingJuly 2026 — Monthly DigestJune 2026 — Monthly DigestLaguna S 2.1Liquid AIMoonshot AIMuse GlimmerOpen-Weights Policy FightPoolsideQwen 3.8 27BQwen 3.8 MaxThinking Machines LabWeekly Synthesis — W30 (July 20–26, 2026)Weekly Synthesis — W31 (July 27 – August 2, 2026)
Sources
- sources/blogs/moonshot-2026-07-16-kimi-k3.md
- sources/blogs/moonshot-2026-07-27-kimi-k3-weights.md
- https://simonwillison.net/2026/Jul/16/kimi-k3/
- https://www.tomshardware.com/tech-industry/artificial-intelligence/moonshot-releases-2-8-trillion-parameter-kimi-k3
- https://platform.kimi.ai/docs/guide/kimi-k3-quickstart
- https://huggingface.co/moonshot-ai/kimi-k3