Sennoric is a small independent lab that publishes its Solan models’ safety results before each release. There are no ads or watermarks in your chats.
Solan Fresco 1.3
Every one of these is written down, and every one links to the page that shows it.
It can also read your Notion pages and GitHub repositories once you connect them in Settings.
Within a point of Claude Sonnet 3.5 on the harder EvalPlus set.
Ahead of Claude Sonnet 3.5's 74.3% on the same benchmark.
Choosing and calling tools correctly on a function-calling test.
Every adversarial scenario, every run, published in full.
Fresco 1.3 was trained by a small independent lab. On the harder “plus” version of HumanEval it sits alongside models from much larger labs.
Reported scores from the EvalPlus leaderboard, accessed September 2026. Test settings differ between providers, so this is a reported-score comparison rather than one controlled run.
Generated text can be shaped so it carries a hidden signature, and a conversation can be sold as ad space. Neither shows on the page. Hold the lamp over both sheets.Develop both sheets below.
A sourdough˙ starter wants a warm⁚ spot and a little patience. Feed it once˙ a day with equal parts flour and water,ˑ and by the fifth day it should double⁚ within six hours.
If it smells˙ like nail polish, it is hungry, not dead.ˑ Feed it, wait, and the sharp⁚ smell fades by the next morning.˙
A sourdough starter wants a warm spot and a little patience. Feed it once a day with equal parts flour and water, and by the fifth day it should double within six hours.
If it smells like nail polish, it is hungry, not dead. Feed it, wait, and the sharp smell fades by the next morning.
Sheet A carries a statistical watermark and an ad slot. Sheet B is what a Sennoric model returns: the words, and only the words. Why we refuse both
api.sennoric.comprobing…
The default Solan model. It replaced Fresco 1.4 on November 2, 2026. It says it doesn’t know more often instead of guessing, and refuses fewer harmless requests: on the XSTest benchmark, its refusals of safe prompts fell from 15.6% to 12.0%, as measured by Sennoric.
Retired Solan Fresco 1.2.5 Solan Glyph 1.1 Decommissioned September 28, 2026. Why
The Sennoric API implements the OpenAI chat-completions format. An existing client needs a new base URL and model name; the rest of the code is unchanged. Streaming behaves as it does with OpenAI.
Signed-in conversations sync across devices.
Works with the official OpenAI SDKs in any language. Pay as you go from API credits.
An open-source terminal agent that edits files and runs commands.
Starting today, Sennoric Pro costs $10 a month, up from $7. It still includes 10 times Free’s weekly and five-hour usage allowances…
Read announcementToday we’re releasing Tessera, a very small chat model built for research.
Read announcementMost AI explainers open with a wall of definitions and hope some of it sticks. We wanted to try it the other way around.
Read announcementA free Sennoric account is all it takes. Your chats aren’t used for ads, and nothing is hidden in the replies.