Most-used AI models for conversation
DeepSeek V4 Flash 0423 is the most-used model for conversation on OpenRouter, handling 18.2% of requests classified as conversation over the last 7 days.
This ranks models by how often they are actually chosen for conversation 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 | 18.2% | 12.0% | $0.140 | 1.0M |
| 2 |  MiMo-V2.5 | 4.2% | 13.5% | $0.140 | 1.1M |
| 3 |  Qwen3.7 Plus | 4.1% | 0.30% | $0.320 | 1M |
| 4 |  Gemini 3 Flash Preview | 4.1% | 2.2% | $0.500 | 1.0M |
| 5 |  Hy3 | 3.3% | 11.5% | $0.132 | 262K |
| 6 | Gemini 2.5 Flash | 3.3% | 0.90% | $0.300 | 1.0M |
| 7 | ILing-2.6-flash | 2.8% | 0.40% | $0.010 | 262K |
| 8 | Gemini 3.1 Flash Lite | 2.5% | 1.4% | $0.250 | 1.0M |
| 9 |  GPT-4o-mini | 2.3% | 0.40% | $0.150 | 128K |
| 10 |  Llama 4 Maverick | 2.2% | 0.30% | $0.200 | 1.0M |
Reading the two columns together: MiMo-V2.5, Hy3 take a noticeably larger share of tokens than of requests — meaning they are being used for the longer, heavier conversation jobs rather than quick one-shot calls.
Frequently asked
DeepSeek V4 Flash 0423 is the most-used model for conversation on OpenRouter, handling 18.2% of requests classified as conversation over the last 7 days. It is followed by MiMo-V2.5 (4.2%) and Qwen3.7 Plus (4.1%).
No. This ranks by how often each model is actually chosen for conversation 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.
Conversation accounts for 2.8% of classified requests and 3.6% 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.