CASE FILE / Model & agent routing
I used Jev to classify 1,018 AI research papers
I used Jev to classify 1,018 AI research papers. The result: $0.08 total cost and 256ms median end-to-end latency per paper. The pipeline was: 1. Summarize each paper with DeepSeek V4 Flash 2. Send the title + summary + 24 possible topics to Jev 3. Use Jev to classify each paper 4. Visualize everything on https://t.co/hs63SlHxjw The summaries cost $3.99 on @togethercompute. The classifications cost $0.08 on @typesafeai. So for just over $4 of inference, I ended up with a pretty useful way to explore the top AI research papers from the past year. I think this is where things are heading: different models for different parts of the workflow, instead of using one model for everything. I’m running evals on the Jev classifications before replacing the current ones, but the site is already live: https://t.co/hs63SlHxjw
Original post
I used Jev to classify 1,018 AI research papers. The result: $0.08 total cost and 256ms median end-to-end latency per paper. The pipeline was: 1. Summarize each paper with DeepSeek V4 Flash 2. Send the title + summary + 24 possible topics to Jev 3. Use Jev to classify each paper 4. Visualize everything on https://t.co/hs63SlHxjw The summaries cost $3.99 on @togethercompute. The classifications cost $0.08 on @typesafeai. So for just over $4 of inference, I ended up with a pretty useful way to explore the top AI research papers from the past year. I think this is where things are heading: different models for different parts of the workflow, instead of using one model for everything. I’m running evals on the Jev classifications before replacing the current ones, but the site is already live: https://t.co/hs63SlHxjw
Chinese translation
我使用Jev对1，018篇人工智能研究论文进行了分类。 结果：总成本为0.08美元，每张纸张的端到端延迟中位数为256 ms。 管道是： 1.使用DeepSeek V4 Flash总结每份论文 2.将标题+摘要+ 24个可能的主题发送给Jev 3.使用Jev对每张论文进行分类 4.在https://t.co/hs63SlHxjw上可视化所有内容 @togethercompute上的摘要售价为3.99美元。@typesafeai上的分类费用为0.08美元。 因此，只需花费4美元多一点的推断，我最终找到了一种非常有用的方法来探索过去一年的顶级人工智能研究论文。 我认为这就是事情的发展方向：针对工作流程的不同部分使用不同的模型，而不是针对所有内容使用一个模型。 在替换当前的分类之前，我正在对Jev分类进行evals，但该网站已经上线：https://t.co/hs63SlHxjw
What this case shows
- Let JEV choose the model or tool first
- Auto-route on high confidence, escalate otherwise
- This is the most common production pattern