Reka Edge

Fiabilité 20%

rekaai/reka-edge

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding, video analysis, object detection, and agentic tool-use.

🧠 Intelligence & Données
Knowledge Cutoff: Inconnue
Tokenizer: Other
Moderation: ✅ Non
📅 Cycle de vie
Ajouté le: 20/03/2026
Spécifications
  • Provider & Modalité rekaai text+image+video->text
  • Fenêtre de contexte 16,384 tokens
  • Max Output Tokens 16,384
  • Support des Outils (Tools) ✔️ Fonction Calling
🔍 Modèles similaires
Modèle Provider Input Output Contexte
Google: Gemma 3n 2B (free)
google/gemma-3n-e2b-it:fr...
google $0.0000 $0.0000 8,192
Google: Gemma 3n 4B (free)
google/gemma-3n-e4b-it:fr...
google $0.0000 $0.0000 8,192
Reka Flash 3
rekaai/reka-flash-3
rekaai $0.1000 $0.2000 65,536
Microsoft: Phi 4
microsoft/phi-4
microsoft $0.0650 $0.1400 16,384
Sao10K: Llama 3.1 70B Hanami x1
sao10k/l3.1-70b-hanami-x1
sao10k $3.0000 $3.0000 16,000