Most-used AI models for content writing
DeepSeek V4 Flash 0423 is the most-used model for content writing on OpenRouter, handling 15.6% of requests classified as content writing over the last 7 days.
This ranks models by how often they are actually chosen for content writing 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 | 15.6% | 16.6% | $0.140 | 1.0M |
| 2 |  Gemini 2.5 Flash Lite | 6.3% | 2.1% | $0.100 | 1.0M |
| 3 | Gemma 3 27B | 6.2% | 2.5% | $0.080 | 262K |
| 4 | Gemini 2.5 Flash | 6.2% | 2.2% | $0.300 | 1.0M |
| 5 |  Llama 4 Maverick | 5.7% | 0.50% | $0.200 | 1.0M |
| 6 | ILing-2.6-flash | 5.5% | 0.60% | $0.010 | 262K |
| 7 | Gemini 3 Flash Preview | 4.2% | 2.9% | $0.500 | 1.0M |
| 8 |  GPT-4o-mini | 3.5% | 0.70% | $0.150 | 128K |
| 9 | Gemini 3.1 Flash Lite | 3.3% | 2.6% | $0.250 | 1.0M |
| 10 |  Mistral Nemo | 3.1% | 0.40% | $0.019 | 131K |
Frequently asked
DeepSeek V4 Flash 0423 is the most-used model for content writing on OpenRouter, handling 15.6% of requests classified as content writing over the last 7 days. It is followed by Gemini 2.5 Flash Lite (6.3%) and Gemma 3 27B (6.2%).
No. This ranks by how often each model is actually chosen for content writing 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.
Content Writing accounts for 5.7% of classified requests and 2.7% 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.