Meta: Llama 4 Maverick
meta-llama/llama-4-maverick
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
Modalities
TextImage
In / out price
₩351 / ₩1,221
1M
Context
10.49 लाख
रिलीज़
6 अप्रैल 2025
Apps
वे ऐप्स जो इस मॉडल का सबसे अधिक उपयोग करते हैं।
| Apps | tokens |
|---|---|
| Hermes Agent | 1.13 नील |
| Zazen (Freebuff fork) | 31.59 ख॰ |
| Cline | 25.57 ख॰ |
| Kilo Code | 24.42 ख॰ |
| pi | 15.88 ख॰ |
| OpenClaw | 10.46 ख॰ |
| Codex | 9.39 ख॰ |
| DeepSeek Harness | 8.47 ख॰ |
| Portkey AI | 6.39 ख॰ |
| HighLevel | 3.75 ख॰ |
| ISEKAI ZERO | 3.65 ख॰ |
| Framer | 3.49 ख॰ |
| Hello Minds, powered by Ethoswarm | 3.17 ख॰ |
| ZCode | 2.8 ख॰ |
| Descript | 2.53 ख॰ |