$ cat wiki/models/kimi-k3.md
Kimi K3
modelupdated 2026-07-20created 2026-07-20
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 | Open-weight (weights release by 2026-07-27) |
| Availability | Kimi Code, Kimi app, Kimi API |
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 (by July 27) |
| Qwen 3.8 Max (Preview) | ~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