DeepSeek V4 Flash 0423 is the most-used model for finance & trading on OpenRouter, handling 11.1% of requests classified as finance & trading over the last 7 days.
This ranks models by how often they are actually chosen for finance & trading 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 | 11.1% | 10.9% | $0.140 | 1.0M | |
| 2 | 9.4% | 10.9% | $0.435 | 1.0M | |
| 3 | 6.1% | 5.8% | $0.760 | 1.0M | |
| 4 | 5.4% | 3.3% | $0.589 | 262K | |
| 5 | 5.4% | 0.80% | $0.300 | 1.0M | |
| 6 | 4.2% | 0.10% | $0.257 | 164K | |
| 7 | 4.0% | 10.6% | $0.140 | 1.0M | |
| 8 | 3.7% | 0.90% | $0.500 | 1.0M | |
| 9 | 2.8% | 11.3% | $0.132 | 262K | |
| 10 | 2.7% | 0.40% | $0.150 | 128K |
Reading the two columns together: DeepSeek V4 Flash 0423, Hy3 take a noticeably larger share of tokens than of requests — meaning they are being used for the longer, heavier finance & trading jobs rather than quick one-shot calls.
DeepSeek V4 Flash 0423 is the most-used model for finance & trading on OpenRouter, handling 11.1% of requests classified as finance & trading over the last 7 days. It is followed by DeepSeek V4 Pro (9.4%) and GLM 5.2 (6.1%).
No. This ranks by how often each model is actually chosen for finance & trading 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.
Finance & Trading accounts for 0.60% of classified requests and 0.50% of classified tokens on OpenRouter over the trailing 7 days.
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.