Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio
15 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
24 providers
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
17 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Inkling Smallthinkingmachines/inkling-small | Thinkingmachines |
52.9 | 1.04858M | $0.58 | $1.44 | 2026-07-30 | ||
| Inklingthinkingmachines/inkling | Thinkingmachines |
52.1 | 1.04858M | $1.87 | $4.68 | 2026-07-15 | ||
| Nemotron 3 Ultra 550B A55Bnvidia/nemotron-3-ultra-550b-a55b | NVIDIA |
49.3 | 1M | $0.1 | $0.1 | 2026-06-04 |