Meta: Llama 4 Scout
Fiabilité
20%
meta-llama/llama-4-scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant...
🧠 Intelligence & Données
Knowledge Cutoff:
2024-08-31
Tokenizer:
Llama4
Moderation:
✅ Non
📅 Cycle de vie
Ajouté le:
05/04/2025
Spécifications
-
Provider & Modalité meta-llama text+image->text
-
Fenêtre de contexte 327,680 tokens
-
Max Output Tokens 16,384
-
Support des Outils (Tools) ✔️ Fonction Calling
🔍 Modèles similaires
| Modèle | Provider | Input | Output | Contexte | |
|---|---|---|---|---|---|
|
Google: Gemma 4 26B A4B
google/gemma-4-26b-a4b-it
|
$0.1300 | $0.4000 | 262,144 | → | |
|
Google: Gemma 4 31B
google/gemma-4-31b-it
|
$0.1400 | $0.4000 | 262,144 | → | |
|
Z.ai: GLM 5V Turbo
z-ai/glm-5v-turbo
|
z-ai | $1.2000 | $4.0000 | 202,752 | → |
|
Arcee AI: Trinity Large Thinking
arcee-ai/trinity-large-th...
|
arcee-ai | $0.2200 | $0.8500 | 262,144 | → |
|
Kwaipilot: KAT-Coder-Pro V2
kwaipilot/kat-coder-pro-v...
|
kwaipilot | $0.3000 | $1.2000 | 256,000 | → |