Most-used AI models for data extraction
DeepSeek V4 Flash 0423 is the most-used model for data extraction on OpenRouter, handling 13.9% of requests classified as data extraction over the last 7 days.
This ranks models by how often they are actually chosen for data extraction 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 | 13.9% | 17.8% | $0.140 | 1.0M |
| 2 |  Gemini 2.5 Flash Lite | 9.8% | 5.2% | $0.100 | 1.0M |
| 3 | ILing-2.6-flash | 6.7% | 4.2% | $0.010 | 262K |
| 4 | Gemini 2.5 Flash | 6.5% | 4.2% | $0.300 | 1.0M |
| 5 | Gemini 3.1 Flash Lite | 6.2% | 4.1% | $0.250 | 1.0M |
| 6 |  Llama 3.1 8B Instruct | 3.8% | 0.80% | $0.050 | 131K |
| 7 |  gpt-oss-120b | 3.6% | 2.6% | $0.037 | 131K |
| 8 | GPT-4o-mini | 3.3% | 1.4% | $0.150 | 128K |
| 9 | Gemini 3 Flash Preview | 3.3% | 2.5% | $0.500 | 1.0M |
| 10 | GPT-5.6 Luna | 2.7% | 3.4% | $0.100 | 1.1M |
Frequently asked
DeepSeek V4 Flash 0423 is the most-used model for data extraction on OpenRouter, handling 13.9% of requests classified as data extraction over the last 7 days. It is followed by Gemini 2.5 Flash Lite (9.8%) and Ling-2.6-flash (6.7%).
No. This ranks by how often each model is actually chosen for data extraction 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 Extraction accounts for 14.7% of classified requests and 5.1% 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.