aiq/routingarea/agenthelp wantedkind/enhancementkind/featurepriority/p2status/bot-triaged
Métriques du dépôt
- Stars
- (103 992 stars)
- Métriques de merge PR
- (Merge moyen 4j 2h) (55 PRs mergées en 30 j)
Description
What would you like to be added?
I would like to have much more control over routing. For numerical routing, this would mean controlling what levels get sent to which models, for example something like:
- <10 -> local gemma
- <30 -> 2.5 flash
- <80 -> 3 flash
- >80 -> 3 pro
Why is this needed?
Currently, the only routing available is to choose between the flash and pro models for the current major version. This is quite restrictive, especially as even 3 flash is quite capable (and quite quota- and rate-limited).
Additional context
No response