Inception: Mercury 2

Fiabilité 20%

inception/mercury-2

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving >1,000 tokens/sec on standard GPUs. Mercury 2 is 5x+ faster than leading speed-optimized LLMs l...

🧠 Intelligence & Données
Knowledge Cutoff: Inconnue
Tokenizer: Other
Moderation: ✅ Non
📅 Cycle de vie
Ajouté le: 04/03/2026
Spécifications
  • Provider & Modalité inception text->text
  • Fenêtre de contexte 128,000 tokens
  • Max Output Tokens 50,000
  • Support des Outils (Tools) ✔️ Fonction Calling
🔍 Modèles similaires
Modèle Provider Input Output Contexte
OpenAI: GPT-5.3 Chat
openai/gpt-5.3-chat
openai $1.7500 $14.0000 128,000
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
google/gemini-3.1-flash-i...
google $0.5000 $3.0000 65,536
AionLabs: Aion-2.0
aion-labs/aion-2.0
aion-labs $0.8000 $1.6000 131,072
Z.ai: GLM 5
z-ai/glm-5
z-ai $0.7200 $2.3000 80,000
Arcee AI: Trinity Large Preview (free)
arcee-ai/trinity-large-pr...
arcee-ai $0.0000 $0.0000 131,000