Web search for every Shannon model
Every model in Shannon's lineup can now get a real, cited answer from the web, even the ones that never had search of their own — so a cheaper model doesn't have to guess or refuse when a question needs today's answer.
Shannon can now get a real, cited answer from any model in the lineup, even the ones that have never had search of their own. Ask something that needs a current answer while Auto has you on one of the cheaper models, and instead of guessing or admitting it can’t search, Shannon searches and answers from what’s online right now.
Shannon runs on more than one model on purpose. That’s the Mixture of Models principle: each task goes to whichever one does it best today. That promise only holds if every model in the lineup can do the job, and until now, most of them couldn’t do this one.
Up-to-date answers from lighter models
Only a few models in Shannon’s lineup could search the web on their own: Sonnet, Opus, and Gemini. Everything else Auto reaches for on lighter, cheaper work — Qwen3-Next, Kimi K2 Thinking, GLM-5, Grok, and gpt-oss-120b among them — had no search at all. Before this, a question that needed the web had two bad paths: route to a premium model that could search, or land on a lighter model that had to refuse or answer from stale training data. The fallback gives those lighter models the same escape hatch: web search without premium routing.
When Shannon searches, it shows the query it ran and the sources it cited. In one test, the model’s query showed it still had an old Python version, derived from its training data. The live results corrected the answer before it reached the user. And when a search comes back empty, Shannon says so instead of filling the gap with a guess.
Under the hood
The fallback wraps Gemini’s own web-search grounding as a one-shot call any model can reach for. The agent asks for a search, one Gemini call runs it and returns a grounded answer with citations, and that result comes back as the tool’s output to whichever model is doing your work. The citation links point through Google’s own redirect domain rather than the original URL, so the plain source name next to each one (wikipedia.org, python.org) is what tells you where the answer came from.
Try it at shannon.bot, no sign-in needed: ask something that needs a current answer and watch the sources show up.