Google: Gemma 4 31B

Fiabilité 20%

google/gemma-4-31b-it

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, a...

🧠 Intelligence & Données
Knowledge Cutoff: Inconnue
Tokenizer: Gemma
Moderation: ✅ Non
📅 Cycle de vie
Ajouté le: 02/04/2026
Spécifications
  • Provider & Modalité google text+image+video->text
  • Fenêtre de contexte 262,144 tokens
  • Max Output Tokens 131,072
  • Support des Outils (Tools) ✔️ Fonction Calling
🔍 Modèles similaires
Modèle Provider Input Output Contexte
Google: Gemma 4 26B A4B
google/gemma-4-26b-a4b-it
google $0.1300 $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
Google: Lyria 3 Pro Preview
google/lyria-3-pro-previe...
google $0.0000 $0.0000 1,048,576
Google: Lyria 3 Clip Preview
google/lyria-3-clip-previ...
google $0.0000 $0.0000 1,048,576