# Inception releases Mercury 3 with 1M-token context

_Published Monday, October 19, 2026 at 4:07 PM EDT · AI · Latest · Tier 2 — Notable_

![Inception releases Mercury 3 with 1M-token context — Primary](https://framerusercontent.com/images/Zgp1I1AaILVgkXF4Xlk7iImaE.png?width=1200&height=630)

Inception made Mercury 3 available through its API platform, OpenRouter, Baseten and Vercel, the company announced. The text model has a 1M-token context window, up from 260K for Mercury 2.5, allowing more material to be included in a request.

Inception reports generation speed of 1,068 tokens per second on NVIDIA GPUs. Standard pricing is $0.20 per million input tokens and $0.70 per million output tokens; launch pricing is 50% off at $0.10 and $0.35, respectively.

The company says early-access partners use Mercury 3 for customer support, tutoring, data engineering and web navigation. Its API is compatible with the OpenAI API, and enterprise deployments support dedicated capacity and configurable data retention.

## Sources

- [inceptionlabs.ai](https://www.inceptionlabs.ai/blog/introducing-mercury-3)

---
Canonical: https://techandbusiness.org/newswire/KTdFDffNksIIFnGofrc0wk
Published: 2026-10-19T20:07:25.015Z
Story chronology: 2026-10-19T17:27:11.000Z
Retrieved: 2026-10-19T22:49:53.080Z
Publisher: Tech & Business (techandbusiness.org)