The world's largest open-weight AI model - 2.8 trillion parameters, 1 million token context, native vision and video, and #1 on the Frontend Code Arena. Available now via API and kimi.com. Open weights shipping July 27, 2026.
K3 is built on two architectural innovations that separate it from every prior Kimi model: a new sparse MoE layout called Stable LatentMoE with 896 experts, and Kimi Delta Attention (KDA) - a hybrid linear-attention mechanism that delivers up to 6.3× faster decoding at 1M token context lengths.
reasoning_effort dial. At launch, the dial ships locked to maximum. Lighter and heavier modes are promised in a post-launch update.K3 doesn't win every benchmark - and Moonshot says so plainly in its launch post. It trails Claude Fable 5 and GPT-5.6 Sol overall. What it does deliver is genuine SOTA performance in specific high-value lanes: coding, frontend, long-horizon agentic work, and document-scale knowledge tasks.
K3 beats Opus 4.8 and GPT-5.5 outright. It wins specific benchmarks against Fable 5 and GPT-5.6 Sol while trailing them on overall intelligence. Open weights, price, and the scale gap make it a different kind of story than a benchmark table can fully capture.
| Kimi K3Moonshot AI · Jul 16, 2026 | Claude Fable 5Anthropic · 2026 | GPT-5.6 SolOpenAI · 2026 | Claude Opus 4.8Anthropic · 2026 | GPT-5.5OpenAI · 2026 | |
|---|---|---|---|---|---|
| Architecture | |||||
| Total parameters | 2.8T MoE | ~unknown | ~unknown | ~200B | ~200B |
| Open weights | ✓ Jul 27 · Mod. MIT | ✗ | ✗ | ✗ | ✗ |
| Context window | 1M tokens | 200K | 1M | 200K | 1M |
| Native multimodal | Text + Image + Video | Text + Image | Text + Image | Text + Image | Text + Image |
| Always-on thinking | ✓ effort dial | ✓ | ✓ | ✓ | Partial |
| Benchmark performance | |||||
| AA Intelligence Index | 57 #4 | ~60 #1 | ~59 #2 | ~56 | ~51 |
| LMArena Frontend Code | 1,679 Elo #1 | 1,612 Elo | 1,589 Elo | 1,531 Elo | ~1,480 |
| GPQA Diamond | 93.5% Best open | ~96% | ~95% | ~89% | ~84% |
| SWE Marathon | 42.0 SOTA | 35.0 | 37.2 | 40.0 | 28.0 |
| Terminal-Bench 2.1 | 88.3 #2 | 86.1 | 88.8 #1 | 82.4 | 74.2 |
| BrowseComp | 91.2% SOTA | 88.4% | 87.6% | 83.2% | 74.8% |
| Program Bench | 77.8 SOTA | 77.1 | 77.6 | 74.3 | 68.9 |
| AA Coding Index | 76.24 #1 | 74.8 | 73.2 | 69.1 | 61.4 |
| AA-Briefcase Elo | 1,547 #2 | ~1,620+ | ~1,590 | ~1,480 | ~1,390 |
| Cost & speed | |||||
| API input / 1M tokens | $3.00 (or $0.30 cached) | $50.00+ | ~$15.00 | ~$15.00 | ~$5.00 |
| API output / 1M tokens | $15.00 | ~$50.00 | ~$60.00 | ~$75.00 | ~$30.00 |
| Cost per task (typical) | ~$0.94 | ~$3.20 | ~$1.04 | ~$1.80 | ~$1.20 |
| Decoding at 1M context | 6.3× KDA boost | Standard | Standard | Standard | Standard |
Competitor figures at max reasoning effort where comparable. Independent AA scores. Fable 5 / GPT-5.6 Sol / Opus 4.8 scores from Artificial Analysis and Moonshot's published launch comparison. All figures current as of July 17, 2026.
Kimi K3 is live now on the Kimi API. OpenAI and Anthropic SDK compatible - change two lines from your existing Claude or GPT setup. Mooncake serving infrastructure keeps cache hit rates above 90% on coding tasks, making the effective cost far lower than the headline rate.
Model ID: kimi-k3 (Kimi Code: /model k3)
Moderato ($19/mo): 256K context max
Allegretto ($39/mo): Full 1M context
Direct API: Full 1M with max_tokens: 1048576
1M tokens holds ~750,000 lines of code. Load an entire monorepo, all dependencies and configuration files, and have K3 reason about the full system at once - no chunking, no retrieval overhead.
~750,000 words per session - roughly 10 full novels or 3,000 research papers. Legal due diligence, multi-document contract analysis, regulatory filing review in one pass.
Frame-by-frame video reasoning within the 1M token window. Ask temporal questions about what changes across hundreds of frames. Unique to K3 in the Kimi lineup.
Extended multi-turn agentic sessions that maintain full context across hundreds of tool calls without forgetting early decisions. K3's 1M window is why SWE Marathon scores beat models with 200K context.
KDA hybrid attention makes the 1M window actually usable - not just a number on a spec sheet. Standard quadratic attention at 1M context is impractically slow; KDA's linear recurrence changes that.
Long-form financial models, annual reports, multi-year regulatory submissions. K3 can hold an entire year's worth of enterprise documentation in a single context and reason across it all.
Official Kimi K3 Demo - Frontend Code Arena #1 Performance
Kimi K3 Benchmark Comparison - Full Scorecard
K3 + Kimi Code - Full Codebase Analysis Session
K3 Open Weights - Self-Hosting Guide (July 27)
K3 is live at kimi.com and the Kimi mobile app. Select K3 from the model switcher. Full 1M context requires Allegretto plan ($39/mo). Moderato users get 256K. Free users get basic access. Native image and video upload supported in all tiers.
Model ID: kimi-k3 and kimi-k3-swarm-max. Base URL: https://api.moonshot.ai/v1. OpenAI and Anthropic SDK compatible. Get your key at platform.kimi.ai. Pricing: $0.30 cached / $3.00 uncached input · $15.00 output.
Switch to K3 in an active Kimi Code session: type /model k3. Or start with kimi --model k3. K3 is Moonshot's most capable coding model but uses more tokens per session. Best for complex long-session work where quality matters more than cost.
Full 2.8T weights release on July 27 under Modified MIT license. Repo: github.com/MoonshotAI/Kimi-K3. Deployment requires A100-class GPU clusters. Supported engines: vLLM, SGLang, TensorRT-LLM. Technical report ships on the same date. Commercial use permitted.