modelgrep

Most-used AI models for sql & database

Match · Updated 2026-08-04

DeepSeek V4 Flash 0423 is the most-used model for sql & database on OpenRouter, handling 10.5% of requests classified as sql & database over the last 7 days.

0.20%of all requests
0.50%of all tokens
7dwindow

This ranks models by how often they are actually chosen for sql & database 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.

#ModelRequest shareToken shareInput /MContext
1deepseek logoDeepSeek V4 Flash 042310.5%8.0%$0.1401.0M
2xiaomi logoMiMo-V2.58.3%13.8%$0.1401.1M
3z-ai logoGLM 5.26.9%6.6%$0.7601.0M
4deepseek logoDeepSeek V4 Pro5.6%5.8%$0.4351.0M
5deepseek logoDeepSeek V4 Flash 04234.7%8.0%$0.1401.0M
6anthropic logoClaude Haiku 4.54.6%1.1%$1.00200K
7openai logoGPT-5.6 Luna3.5%6.7%$0.1001.1M
8stepfun logoStep 3.7 Flash3.4%6.3%$0.200262K
9openai logoGPT-52.9%0.40%$1.25400K
10tencent logoHy32.8%4.0%$0.132262K

Reading the two columns together: MiMo-V2.5, DeepSeek V4 Flash 0423, GPT-5.6 Luna take a noticeably larger share of tokens than of requests — meaning they are being used for the longer, heavier sql & database jobs rather than quick one-shot calls.

Frequently asked

What is the most-used AI model for sql & database?

DeepSeek V4 Flash 0423 is the most-used model for sql & database on OpenRouter, handling 10.5% of requests classified as sql & database over the last 7 days. It is followed by MiMo-V2.5 (8.3%) and GLM 5.2 (6.9%).

Is this a benchmark ranking?

No. This ranks by how often each model is actually chosen for sql & database 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.

How much of all AI traffic is sql & database?

SQL & Database accounts for 0.20% of classified requests and 0.50% 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.