Most-used AI models for customer support
Gemini 2.5 Flash is the most-used model for customer support on OpenRouter, handling 22.6% of requests classified as customer support over the last 7 days.
This ranks models by how often they are actually chosen for customer support 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 |  Gemini 2.5 Flash | 22.6% | 8.2% | $0.300 | 1.0M |
| 2 |  DeepSeek V4 Flash 0423 | 10.1% | 12.1% | $0.140 | 1.0M |
| 3 | Gemini 3 Flash Preview | 7.7% | 8.7% | $0.500 | 1.0M |
| 4 |  GPT-5.4 Nano | 5.4% | 4.1% | $0.200 | 400K |
| 5 | Gemini 3.1 Flash Lite | 3.9% | 5.2% | $0.250 | 1.0M |
| 6 | gpt-oss-120b | 2.6% | 1.0% | $0.037 | 131K |
| 7 | GPT-5.6 Luna | 2.6% | 3.8% | $0.100 | 1.1M |
| 8 | GPT-4.1 Mini | 2.4% | 2.2% | $0.400 | 1.0M |
| 9 | GPT-4o-mini | 2.3% | 1.1% | $0.150 | 128K |
| 10 | GPT-5.4 Mini | 2.3% | 1.5% | $0.750 | 400K |
Frequently asked
Gemini 2.5 Flash is the most-used model for customer support on OpenRouter, handling 22.6% of requests classified as customer support over the last 7 days. It is followed by DeepSeek V4 Flash 0423 (10.1%) and Gemini 3 Flash Preview (7.7%).
No. This ranks by how often each model is actually chosen for customer support 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.
Customer Support accounts for 2.1% of classified requests and 1.5% 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.