Kimi K3 is Moonshot AI's open-weight successor to Kimi K2 — a 2.8T-parameter, 104B-activated MoE model built on a new Kimi Delta Attention (KDA) architecture, with native multimodal vision, a 1,048,576-token context window, and published benchmarks against Claude and GPT-class frontier models.
- ⭐ 8176
- Python
- Kimi K3 License
- Updated 2026-08-08
[1M Context Window LLM 2026: Real Tests](https://dibi8.com/resources/llm-frameworks/1m-context-window-llm-2026-real-test/) •
[Open Interpreter: A Codex Fork That Emulates Claude Code and Kimi’s Harness](https://dibi8.com/resources/llm-frameworks/openinterpreter-low-cost-model-coding-agent-2026/)
Kimi K3 — from github.com/MoonshotAI/Kimi-K3
What Is Kimi K3? # #
Kimi K3 is Moonshot AI’s newest open-weight model, and per the README, their most capable to date: a 2.8-trillion-parameter Mixture-of-Experts model with 104B activated parameters per token, built on a new Kimi Delta Attention (KDA) and Attention Residuals (AttnRes) architecture. Moonshot AI describes it as “the world’s first open 3T-class model” — native multimodal (text, image, video-frame understanding), a 1,048,576-token context window, and released with full weights under a custom Kimi K3 License.
🔗 **GitHub**: [https://github.com/MoonshotAI/Kimi-K3](https://github.com/MoonshotAI/Kimi-K3)
🤗 **Weights**: [huggingface.co/moonshotai/Kimi-K3](https://huggingface.co/moonshotai/Kimi-K3)
📄 Tech report: linked from the repo as k3_tech_report.pdf
At 8,100+ GitHub stars, created July 27, 2026 and pushed as recently as August 6, 2026.
Architecture: What Changed From K2 # #
| Spec | Value |
|---|---|
| Total parameters | 2.8T |
| Activated parameters | 104B |
| Layers | 93 (1 dense + 92 MoE) |
| Attention composition | 69 KDA + 24 Gated MLA |
| Attention heads | 96 (hidden dim 7168) |
| Experts | 896 total, 16 selected/token, 2 shared |
| Vocabulary | 160K tokens |
| Context length | 1,048,576 tokens |
| Vision encoder | MoonViT-V2 (401M params) |
| Quantization | Native MXFP4 weights / MXFP8 activations (quantization-aware trained) |
Per Moonshot AI, the Stable LatentMoE framework activating 16 of 896 experts yields “an approximate 2.5× improvement in overall scaling efficiency” over K2. The quantization detail is worth flagging separately: MXFP4/MXFP8 is trained in from the SFT stage onward, not bolted on as a post-hoc compression step — the stated goal being broad hardware compatibility without a separate quantization pass degrading quality.
Benchmark Highlights (Self-Reported, Max Effort) # #
Moonshot AI’s README publishes a large comparison table against Claude Fable 5, Claude Opus 4.8, GPT-5.6 Sol, GPT-5.5, and GLM-5.2. A representative slice — K3 doesn’t sweep every category, and the pattern shifts by benchmark type:
| Benchmark | Kimi K3 | Best of the rest |
|---|---|---|
| BrowseComp (agentic web) | 91.2 | GPT-5.6 Sol 90.4 |
| MCPMark-Verified (MCP tool use) | 94.5 | GPT-5.6 Sol / GPT-5.5 tied 92.9 |
| Terminal-Bench 2.1 | 88.3 | GPT-5.6 Sol 88.8 | | GPQA Diamond (reasoning) | 93.5 | GPT-5.6 Sol 94.1 | | HLE-Full | 43.5 | Claude Fable 5 53.3 |
| CritPt (physics reasoning) | 23.4 | GPT-5.6 Sol 32.3 |
| Video-MME (w/ subtitles) | 90.0 | GPT-5.6 Sol 89.5 |
| OmniDocBench (document vision) | 91.1 | Claude Fable 5 89.8 |
| Harvey Lab-AA (legal) | 94.6 | Claude Fable 5 93.6 | Read this carefully: these are Moonshot AI’s own numbers from their tech report, not third-party reproductions. K3 leads on agentic tool-use and several vision/document benchmarks, but trails Claude Fable 5 and GPT-5.6 Sol on some of the hardest pure-reasoning evals (HLE-Full, CritPt). Treat it as “strong, benchmark-dependent,” not “best at everything.”
Deployment and Model Usage # #
Recommended inference engines, per the README:
— published recipes at recipes.vllm.aivLLM— cookbook at docs.sglang.ioSGLangTokenSpeed— recipes at lightseek.org
A hosted, OpenAI/Anthropic-compatible API is available at platform.kimi.ai (model name kimi-k3
).
Thinking is always on. Reasoning effort is set via a reasoning_effort
field ("low"
/ "high"
/ "max"
, default "max"
), returned as a separate reasoning_content
field. The one gotcha worth flagging for anyone integrating this: K3 was trained in preserved thinking history mode, meaning multi-turn calls must pass the complete prior assistant message back — reasoning_content
and tool_calls
included, not just the final content
string — or the model loses the thread on follow-up turns.
For an agent harness, Moonshot AI points to their own Kimi Code CLI — run it in a terminal and switch to K3 with the /model
command.
Licensing: What Triggers a Paid Agreement # #
The Kimi K3 License (custom, same shape as K2’s) is permissive by default — free to use, modify, fine-tune, and redistribute — with two revenue-gated conditions:
“Model as a Service” threshold: if you (plus affiliates) give third parties API-level control over K3’s inputs/parameters/fine-tuning and your combined revenue exceeds**$20M USD over any 12 consecutive months**, you need a separate commercial agreement with Moonshot AI.** Attribution at scale**: if K3 powers a product with** 100M+ monthly active usersor$20M+/month revenue**, “Kimi K3” must be prominently displayed in that product’s UI.
Both conditions are waived for internal use and for end-user products that merely embed K3’s capabilities without exposing model-level control to third parties.
## License [#](#license)
**Kimi K3 License** (custom, permissive with revenue-based commercial terms) — see [LICENSE](https://github.com/MoonshotAI/Kimi-K3/blob/main/LICENSE).