Mercury 3
Mercury 3 is Inception's flagship diffusion-based LLM (dLLM), released 2026-10-19 and described as the most capable diffusion LLM released to date. Inception says it is more than 40x larger in total parameters than Mercury 1 and runs at about 1,068 output tokens per second on NVIDIA GPUs while matching or beating speed-optimized models such as GPT-6 Luna and Claude Haiku 5.5. It has a 1M-token context window, up to 131,072 output tokens, tunable reasoning effort (instant, low, medium, high), tool calling, and structured outputs. Text in, text out. Available on the Inception API, OpenRouter, Vercel AI Gateway, and Baseten.
Key Specifications
Timeline
Technical Specifications
Pricing & Availability
Benchmark Results
Model performance metrics across various tests and benchmarks
Reasoning
Other Tests
License & Metadata
Compare Mercury 3
All comparisonsSimilar Models
All ModelsMercury 2
Inception
Solar Pro 4
Upstage
MiMo-V2-Pro
Xiaomi
MiniMax M2.1
MiniMax
Qwen3.7 Max
Alibaba
o1-preview
OpenAI
SWE-2
Cognition
Gemini 3.8 Flash Cyber
Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.