News · 2026-10-26
Mirendil's Fern 0.1 claims a 10M-token context window for agentic work; access still closed
Mirendil, a one-year-old AI lab building systems for AI R&D, published Fern 0.1 on 26 October 2026: its first model, supporting a context window of up to 10 million tokens — about 23 MB of code, roughly half a million lines, a Megatron-LM-scale codebase, or dozens to hundreds of complete agent traces at once. Fern 0.1 is 0.1 to 0.5 trillion parameters, takes text and code input, and is built for high-volume agentic tasks such as working across large repositories, debugging training runs from logs and reading agent traces end to end. Two larger models (0.5 to 2T and 2 to 10T parameters) are in pretraining. Access is listed as coming soon with no pricing disclosed, and the announcement defers comprehensive long-context benchmark results.
What it means for buyers
If the window claim survives independent testing, codebase-scale and trace-scale context stops needing retrieval plumbing, which changes what coding agents and agent platforms can run in one pass — the working context assumptions behind our ai-coding-assistants and ai-agent-builders comparisons. Treat the number as a vendor claim for now: the model is not publicly accessible, the announcement page carries no benchmark scores yet, and company-run long-context results have historically degraded at the far end of the window.
Where to check it
Sources
- Introducing Fern (Mirendil) — launch page: 10M-token context, sizes, intended tasks, access coming soon, published 2026-10-26 8am PT, checked 2026-10-26
- Mirendil unveils Fern, an AI model claiming a 10 million token context window (Startup Fortune) — secondary report adding company-run RULER detail (90-100% retrieval, 45% multi-hop at 10M tokens) not yet on the launch page, checked 2026-10-26