Babble Models by Supermaven
1 model2024
Last refreshed 2026-05-19. Next refresh: weekly.
Links
WebsiteAbout
Babble is the code completion model Supermaven trained for its inline completions and introduced with Supermaven 1.0 in July 2024. Supermaven says Babble is 2.5 times larger than its previous model, was trained on a larger corpus of code for broader knowledge, and expands the context window from 300,000 to 1 million tokens, while serving improvements kept latency low. Babble was deployed to all Supermaven users, and Supermaven Pro users get its full 1 million-token context window.
Decision facts
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Babble | Use when provider availability and model metadata match the workload. | 2024-07 | — | Current |
Release Timeline
1 release group2024-07
1 current
Current
Specifications(1 models)
| Model | Released |
|---|---|
| Babble | 2024-07 |
