Most-used AI models for frontend & ui
MiMo-V2.5 is the most-used model for frontend & ui on OpenRouter, handling 16.4% of requests classified as frontend & ui over the last 7 days.
This ranks models by how often they are actually chosen for frontend & ui in production traffic, not by benchmark score. Adoption reflects price, latency and availability as much as raw capability — which is exactly why it often disagrees with the benchmark leaderboards, and why it is worth reading alongside them.
| # | Model | Request share | Token share | Input /M | Context |
|---|---|---|---|---|---|
| 1 |  MiMo-V2.5 | 16.4% | 17.6% | $0.140 | 1.1M |
| 2 |  DeepSeek V4 Flash 0423 | 7.8% | 8.6% | $0.140 | 1.0M |
| 3 | DeepSeek V4 Flash 0423 | 7.0% | 9.4% | $0.140 | 1.0M |
| 4 |  GPT-5.6 Luna | 6.5% | 7.0% | $0.100 | 1.1M |
| 5 |  GLM 5.2 | 5.7% | 5.9% | $0.760 | 1.0M |
| 6 |  Gemini 3.6 Flash | 5.6% | 3.9% | $1.50 | 1.0M |
| 7 |  Hy3 | 5.3% | 4.8% | $0.132 | 262K |
| 8 | laguna-s-2.1-20260720:free | 4.1% | 4.9% | — | — |
| 9 |  Step 3.7 Flash | 3.9% | 5.2% | $0.200 | 262K |
| 10 | ling-3.0-flash-20260723:free | 3.5% | 3.6% | — | — |
Frequently asked
MiMo-V2.5 is the most-used model for frontend & ui on OpenRouter, handling 16.4% of requests classified as frontend & ui over the last 7 days. It is followed by DeepSeek V4 Flash 0423 (7.8%) and DeepSeek V4 Flash 0423 (7.0%).
No. This ranks by how often each model is actually chosen for frontend & ui in production traffic through OpenRouter — real-world adoption, which reflects price and availability as much as capability. For capability-based rankings, see the benchmark leaderboards.
Frontend & UI accounts for 0.70% of classified requests and 3.3% of classified tokens on OpenRouter over the trailing 7 days.
Other tasks
Source: OpenRouter (openrouter.ai/rankings), as of 2026-08-04. Shares are of classified, sampled traffic over a trailing 7-day window; absolute volumes are not published.