← Tuesday, October 20, 2026InferenceRelease

Mercury 3 claims 1,068 tokens per second with a million-token context

inceptionlabs.ai 5 min read Editor score 6/10

Inception says its diffusion-based LLM reaches 1,068 tokens per second on NVIDIA GPUs, supports a one-million-token context, and costs $0.20 per million input tokens. The release is a concrete claim to evaluate against serving latency, quality, and cost requirements.

What

Mercury 3 is a diffusion-based large language model from Inception.

How

The company reports 1,068 tokens per second on Nvidia GPUs, a one-million-token context and a model more than 40 times larger than Mercury 1.

Why it matters

Fast responses may suit latency-sensitive agents, where delays at successive model steps can compound.

Read on inceptionlabs.ai → Hacker News · 85 comments

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.