Inceptionlabs · Chat
Mercury 3
InceptionlabsChatMercury familyOne of its sources says the weights aren't publicly available.The maker currently plans to deprecate it within the next 180 days (28 Dec 2026). Plans can change.
Mercury 3 is Inception’s most capable model for agentic workflows and real-time applications. It is one of the world’s fastest models, powered by diffusion.
- llminfo IQ
- 129.3
- Market median price
- $0.1625 blended / 1M
- Max context
- 1M
- Listings
- 4
Evidence and sources
llminfo IQ 129.3, ranked among chat models. From 29 benchmarks. Plenty of data behind it.How llminfo IQ is computedPoor value (42.3). Costs more per task than its benchmark results predict. From 11 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksReleased 19 Oct 2026
All rankings:
#129 on OpenRouter this month
#283 on NanoGPT recentlySources: Inception Labs data, Models.dev data, Kilo AI Gateway data, llminfo researchPrimary data from Inception Labs
from Models.dev: weights availability
from Kilo AI Gateway: deprecation date, description
from llminfo research: release date
Advantages and trade-offs
Compared with 10 chat models, picked mainly by popularity and IQ
Advantages
Costs less than most peers
Market median price: $0.1625 blended / 1M, cheaper than 9 of 9 priced peers.
Trade-offs
Deprecation scheduled
The maker plans to deprecate it on 28 Dec 2026, within the next 180 days.
Fewer provider choices
No open weights
The weights aren't public, so you can't run it yourself.
Input & output
as stated by the model's providersText
Text
Also known as: inception/mercury-3
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works