Most-used AI models for devops & config
MiMo-V2.5 is the most-used model for devops & config on OpenRouter, handling 12.5% of requests classified as devops & config over the last 7 days.
This ranks models by how often they are actually chosen for devops & config 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 | 12.5% | 13.1% | $0.140 | 1.1M |
| 2 |  DeepSeek V4 Flash 0423 | 9.8% | 7.7% | $0.140 | 1.0M |
| 3 | DeepSeek V4 Flash 0423 | 9.2% | 10.8% | $0.140 | 1.0M |
| 4 |  GLM 5.2 | 6.2% | 5.0% | $0.760 | 1.0M |
| 5 | nemotron-3-ultra-550b-a55b-20260604:free | 5.9% | 7.3% | — | — |
| 6 | DeepSeek V4 Pro | 5.8% | 5.5% | $0.435 | 1.0M |
| 7 |  GPT-5.6 Luna | 5.1% | 6.6% | $0.100 | 1.1M |
| 8 |  Step 3.7 Flash | 4.6% | 5.2% | $0.200 | 262K |
| 9 | laguna-s-2.1-20260720:free | 4.5% | 5.1% | — | — |
| 10 |  Hy3 | 4.5% | 4.5% | $0.132 | 262K |
Frequently asked
MiMo-V2.5 is the most-used model for devops & config on OpenRouter, handling 12.5% of requests classified as devops & config over the last 7 days. It is followed by DeepSeek V4 Flash 0423 (9.8%) and DeepSeek V4 Flash 0423 (9.2%).
No. This ranks by how often each model is actually chosen for devops & config 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.
DevOps & Config accounts for 0.10% of classified requests and 0.60% 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.