Less context burned. A model lookup used to dump ~1 MB (~250k tokens) into your agent's context. It's now 38 KB, paginated, 96% smaller. Transcripts carry timestamps and speakers in plain text so every client can use them.
OpenRouter cuts model lookup output from 1 MB to 38 KB
AIOpenRouter says a model lookup that previously dumped about 1 MB (roughly 250k tokens) into an agent's context now returns 38 KB, paginated, a 96% reduction. It also says transcripts now carry timestamps and speakers in plain text so any client can use them.
Source details
OpenRouter · x.comPublished · added here
Original title: Less context burned. A model lookup used to dump ~1 MB (~250k tokens) into your agent's context. It's now 38 KB, paginated, 96% smaller. ...