Most-used AI models for data transformation
DeepSeek V4 Flash 0423 is the most-used model for data transformation on OpenRouter, handling 21.9% of requests classified as data transformation over the last 7 days.
This ranks models by how often they are actually chosen for data transformation 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 |  DeepSeek V4 Flash 0423 | 21.9% | 24.2% | $0.140 | 1.0M |
| 2 |  Gemini 2.5 Flash Lite | 10.1% | 5.7% | $0.100 | 1.0M |
| 3 | Gemini 3.1 Flash Lite | 5.3% | 2.2% | $0.250 | 1.0M |
| 4 | Gemini 2.5 Flash | 5.1% | 2.3% | $0.300 | 1.0M |
| 5 | Gemini 3 Flash Preview | 4.3% | 2.6% | $0.500 | 1.0M |
| 6 |  GPT-4o-mini | 3.7% | 1.1% | $0.150 | 128K |
| 7 | gpt-oss-120b | 2.7% | 1.7% | $0.037 | 131K |
| 8 | gpt-oss-20b | 2.6% | 2.8% | $0.030 | 131K |
| 9 | Gemma 4 31B | 2.1% | 1.2% | $0.100 | 262K |
| 10 |  Qwen3.5-Flash | 2.1% | 0.90% | $0.065 | 1M |
Frequently asked
DeepSeek V4 Flash 0423 is the most-used model for data transformation on OpenRouter, handling 21.9% of requests classified as data transformation over the last 7 days. It is followed by Gemini 2.5 Flash Lite (10.1%) and Gemini 3.1 Flash Lite (5.3%).
No. This ranks by how often each model is actually chosen for data transformation 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.
Data Transformation accounts for 3.7% of classified requests and 1.6% 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.