One model. On purpose.
LADLE runs on Claude Sonnet from Anthropic. Every chat, every plan, every seat. No silent downgrade, no per-query routing to a cheaper model.
Sonnet, Opus, Haiku — what we ship and what we don’t.
The model behind every LADLE chat by default. Strong on prose, code, long-context reasoning, and instruction-following. 200K context window.
Anthropic's higher-capability tier, priced meaningfully more per token. LADLE doesn't route to Opus today — including it at $20/mo would either cut the meal donation or lose us money. May change if usage patterns and Opus pricing warrant it.
Anthropic's smaller, faster tier. Great for automated pipelines and high-volume classification. Not a fit for a chat product where the user is a human reading the response.
What runs your query, and what doesn’t.
Every chat runs on Claude Sonnet. Same model, same context window, same generation quality regardless of who's typing or what plan they're on.
We don't silently downgrade Base subscribers to a cheaper model at peak. We don't route "easy" questions to a smaller model to save inference cost. If you're on LADLE, you're on Sonnet.
Anthropic operates the underlying inference infrastructure. They may internally optimize serving without changing model quality — that's fine and expected. What we control is: they say Sonnet, we ship Sonnet.
What it can hold. What it can’t.
The 200K window means the whole 10-K fits. Well past that, the model still tries — but its own reasoning about early parts of a very long context degrades measurably. Practical rule: if your document exceeds 300 pages, chunk to the section you actually care about.
Not opt-out. Not conditional. Not “up to”.
LADLE runs on Anthropic’s API tier where customer data is not used to train Anthropic’s public models by default. We ourselves don’t have models — there’s no scenario where your chats train a “LADLE model” because no such model exists.
If Anthropic ever changes their API tier terms in a way that affects this commitment, we would tell you first — before the effective date — and offer cancellation with a pro-rata refund. Full details in the training-data policy article.
One model. Same one for you. On purpose.
Claude Sonnet, 200K context, no silent downgrade.