Inception releases 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...

Type: MODEL_LAUNCH
Detection: listing
Confidence: medium
Status

Related entities

ModelMercury 2 CompanyInception Labs

Primary source

OpenRouter models API · openrouter.ai/inception/mercury-2 ↗

Structured listing of 400+ hosted models: prices per token, context length, modalities, supported parameters and listing date. Prices are OpenRouter's listed prices, which usually mirror first-party pricing but can differ.