DeepSeek: DeepSeek V3.2 Exp
Fiabilité
20%
deepseek/deepseek-v3.2-exp
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism designed to improve training and inference efficiency in long-context...
🧠 Intelligence & Données
Knowledge Cutoff:
2025-07-31
Tokenizer:
DeepSeek
Moderation:
✅ Non
📅 Cycle de vie
Ajouté le:
29/09/2025
Spécifications
-
Provider & Modalité deepseek text->text
-
Fenêtre de contexte 163,840 tokens
-
Max Output Tokens 65,536
-
Support des Outils (Tools) ✔️ Fonction Calling
🔍 Modèles similaires
| Modèle | Provider | Input | Output | Contexte | |
|---|---|---|---|---|---|
|
Z.ai: GLM 5V Turbo
z-ai/glm-5v-turbo
|
z-ai | $1.2000 | $4.0000 | 202,752 | → |
|
MiniMax: MiniMax M2.7
minimax/minimax-m2.7
|
minimax | $0.3000 | $1.2000 | 204,800 | → |
|
Z.ai: GLM 5 Turbo
z-ai/glm-5-turbo
|
z-ai | $1.2000 | $4.0000 | 202,752 | → |
|
Inception: Mercury 2
inception/mercury-2
|
inception | $0.2500 | $0.7500 | 128,000 | → |
|
OpenAI: GPT-5.3 Chat
openai/gpt-5.3-chat
|
openai | $1.7500 | $14.0000 | 128,000 | → |