LTM Models by Magic
2 models2023–2024Up to 100M ctx
Last refreshed 2026-05-19. Next refresh: weekly.
Details
ResearcherMagic
LicenseProprietary
Commercial useRestricted
Models2
Released2023–2024
Max context100M
Links
WebsiteAbout
LTM (Long-Term Memory) is Magic's model family focused on extreme-scale context windows for software development. LTM-1 (2023) introduced a 5M-token context; LTM-2-mini (2024) extended this to 100M tokens using a novel sequence-dimension algorithm. Developed by Magic (magic.dev), San Francisco.
Decision facts
- Best fit
- codingcode
- Capability starting point
- LTM-2-mini with 100M context
- Lowest tracked input
- Not tracked
- Closest related family
- SWE-1
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
2 in view
LTM-2-miniCurrent
Use when the workload needs code, 100M context, and coding.
2024-08code100M contextcoding
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| LTM-2-mini | Use when the workload needs code, 100M context, and coding. | 2024-08 | code100M contextcoding | Current |
| LTM-1 | Use when the workload needs code, 5M context, and coding. | 2023-06 | code5M contextcoding | Current |
Release Timeline
2 release groups2024-08
1 current
LTM-2-mini
Currentcode100M contextcoding
2023-06
1 current
LTM-1
Currentcode5M contextcoding
Specifications(2 models)
| Model | Released | Context |
|---|---|---|
| LTM-2-mini | 2024-08 | 100M |
| LTM-1 | 2023-06 | 5M |
