# News: 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.

Human page: https://testedactually.com/news/mirendil-fern-10m-context/
Mirror: https://testedactually.com/news/mirendil-fern-10m-context.md
Published: 2026-10-26

## What changed

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.

## Sources

- [1] Introducing Fern (Mirendil) - https://mirendil.com/news/introducing-fern/ (launch page: 10M-token context, sizes, intended tasks, access coming soon, published 2026-10-26 8am PT, checked 2026-10-26)
- [2] Mirendil unveils Fern, an AI model claiming a 10 million token context window (Startup Fortune) - https://startupfortune.com/mirendil-unveils-fern-an-ai-model-claiming-a-10-million-token-context-window/ (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)

TestedActually tracks pricing and programme changes as dated, sourced events: https://testedactually.com/news/.