Use case

Cheap bulk summarization

Shorten a lot of text when a small miss is acceptable and the bill is not.

What matters

Input price times volume is the whole decision. Long context matters only if you refuse to chunk.

cost · long-context

#1ricursiveAI/Ripple-65B-Preview
Listed at a low input price (under $1 / M), which is what bulk work cares about.
#2NVIDIA: Nemotron 3.5 Super VL (free)
Open-weight hint on the listing, so you can check the license and run it yourself.
#3Tencent: Hy4
Open-weight hint on the listing, so you can check the license and run it yourself.

Budget pick

NVIDIA: Nemotron 3.5 Super VL (free)

Open-weight pick

NVIDIA: Nemotron 3.5 Super VL (free)

A decision model will not write the summary. It can score whether a summary followed the rubric.
Free-tier ids are often rate limited. Fine for a sample, painful for a backlog.

Summarize the thread in 5 bullets. Keep names, dates, and the decision. Leave out greetings.