The AcceleratorsStrict ZDR Verified

Inception

Ultra-fast diffusion-architecture inference.

Laboratory Overview

Inception pioneered Diffusion LLMs with the Mercury series, breaking away from conventional autoregressive decoding to generate text through iterative denoising at unprecedented tokens per second.

Core Research Focus:Ultra-fast discrete diffusion inference (>1000 t/s)parallel multi-token refinementlow latency on compounding agent loopstunable reasoning levels.

Privacy & Zero Data Retention

Strict Zero Data Retention (ZDR): Requests are processed ephemerally in RAM. No user data, prompts, or completions are stored, indexed, or used for model training.

No user telemetry sent to Inception

Inception Foundation Models (3)

Available under ARMES unified subscription without separate API keys or billing agreements.

Tier:

Dense Diffusion Transformer (dLLM) — parallel iterative denoising decoding, non-autoregressive

Free

Mercury 3

Mercury 3 (inception/mercury-3) is Inception Labs' flagship diffusion language model (dLLM), released October 19, 2026. It decodes tokens in parallel via iterative denoising rather than strict left-to-right autoregression, pairing a 1M-token context window with a vendor-reported ~1,068 tokens/sec on NVIDIA GPUs and aggressive launch pricing of $0.10/$0.35 per 1M input/output tokens — positioning it as a latency-first alternative to autogregressive speed-tier models like Claude Haiku 5.5 and GPT-6 Luna.

GPQA Diamond:89.2%

1M ctx

$0.20 / $0.70 /MTok

Intelligence Dossier Try in Chat

Dense Diffusion Transformer (dLLM)

Free

Mercury 2.5

Inception's flagship 260K-context diffusion LLM (dLLM), generating and refining text in parallel at over 1,100 tps for real-time agents, code synthesis, and structured workflows accessible with Zero Data Retention on ARMES.

Peak Generation Throughput (NVIDIA Enterprise GPUs):1,107

260K ctx

$0.20 / $0.75 /MTok

Intelligence Dossier Try in Chat

Diffusion LLM

Free

Mercury 2

— | Speed-critical inference, real-time applications, rapid response scenarios

AA Intelligence Index:10.8

128K ctx

$0.25 / $0.75 /MTok

Intelligence Dossier Try in Chat