Most-used AI models for q&a & knowledge
DeepSeek V4 Flash 0423 is the most-used model for q&a & knowledge on OpenRouter, handling 13.1% of requests classified as q&a & knowledge over the last 7 days.
This ranks models by how often they are actually chosen for q&a & knowledge 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 | 13.1% | 14.0% | $0.140 | 1.0M |
| 2 |  Gemini 3 Flash Preview | 4.8% | 2.6% | $0.500 | 1.0M |
| 3 |  GLM 5.2 | 4.3% | 6.1% | $0.760 | 1.0M |
| 4 | Gemini 2.5 Flash | 3.8% | 0.70% | $0.300 | 1.0M |
| 5 | DeepSeek V4 Pro | 3.2% | 6.0% | $0.435 | 1.0M |
| 6 |  GPT-5.6 Luna | 2.9% | 4.6% | $0.100 | 1.1M |
| 7 | Gemini 3.1 Flash Lite | 2.9% | 0.90% | $0.250 | 1.0M |
| 8 | Gemini 2.5 Flash Lite | 2.8% | 0.80% | $0.100 | 1.0M |
| 9 | DeepSeek V4 Flash 0423 | 2.6% | 7.4% | $0.140 | 1.0M |
| 10 |  MiMo-V2.5 | 2.6% | 8.9% | $0.140 | 1.1M |
Reading the two columns together: DeepSeek V4 Pro, GPT-5.6 Luna, DeepSeek V4 Flash 0423 take a noticeably larger share of tokens than of requests — meaning they are being used for the longer, heavier q&a & knowledge jobs rather than quick one-shot calls.
Frequently asked
DeepSeek V4 Flash 0423 is the most-used model for q&a & knowledge on OpenRouter, handling 13.1% of requests classified as q&a & knowledge over the last 7 days. It is followed by Gemini 3 Flash Preview (4.8%) and GLM 5.2 (4.3%).
No. This ranks by how often each model is actually chosen for q&a & knowledge 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.
Q&A & Knowledge accounts for 2.7% of classified requests and 3.0% 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.