MODEL PROFILE / EDITION 2026.09
Kimi K3
Design-led teams and self-hosters who want the best visual-preference model with open weights
Balanced model evidence score; rank 3. No rank delta is shown because there is no prior numeric snapshot.
Best for
Design-led teams and self-hosters who want the best visual-preference model with open weights
Price & access
$3 in / $15 out per 1M with $0.30 cached input (Moonshot); Alibaba resells at $2.827/$14.133 in most regions and $3/$15 in Singapore/US international; OpenRouter median $2.55/$12.75 with $0.256 cache read
Evidence summary
First-party Hugging Face card, two independent human-preference boards (one #1 placement), Alibaba and OpenRouter price rows, and AA measurements. Only the AA index value is disputed.
Edition status
No prior snapshot. Tracked in the September 2026 baseline.
Strengths
- Design Arena Website rank 1 (1361) - the best pure design-preference score in this set
- Arena WebDev Frontend rank 5 (1691) - top open-weight model on that board after Qwen3.8 Max
- Open weights at 2.8T total / 104B active with a 1M context and native vision
- MCPMark-Verified 94.5 and Toolathlon 76.5 make it a genuinely strong tool user
Tradeoffs
- Self-hosting means a ~1.56 TB download and multi-node serving
- $3/$15 API pricing is high for an open-weight model
- AA measured only 40.3 tok/s (OpenRouter providers reach 90)
- AA index figures in circulation conflict (50 at max vs 57 claimed at launch)
Score profile
visual 88 · code 88 · agentic 87 · debug 82 · context 92 · speed 64 · value 74
Linked evidence
Evidence source 1 ↗Evidence source 2 ↗Evidence source 3 ↗Evidence source 4 ↗Evidence source 5 ↗Evidence source 6 ↗Evidence source 7 ↗Evidence source 8 ↗Use the same published data, filters, and side-by-side metrics.