Documentation Index
Fetch the complete documentation index at: https://docs.magnitude.dev/llms.txt
Use this file to discover all available pages before exploring further.
Magnitude gets the most out of open models for coding. We do the testing, tuning, and curation so you don’t have to. You get a coding agent that just works, on the best open models, for $20/month.
The wild west
Open models are now good enough for serious coding. But it’s the wild west. You need to choose a harness, then a model, then a provider. And hope they all play nicely together. Often they don’t, and you get empty thinking output, broken tool calls, and random doom loops.
Our approach
With Magnitude, we’ve bundled the harness, models, and provider into one stack that we continuously test and optimize. We benchmark model combinations to find the best setups, tune our harness to each model’s quirks, and route only to providers serving them correctly and fast. The harness is open source, so you can see exactly what we’re up to.
Our harness only supports the Magnitude Coding Plan. It’s how we can keep the quality bar high and really lean into model capabilities. We think this is even more important for open models, as they are less “one size fits all” and really benefit from mixing and matching. And because of open model economics, we can offer this at $20/month with generous rate limits. Sustainably.
Not for everyone
We know this isn’t for everyone. Some people want the flexibility. Some people want to hack together their own setups. And we respect that. But we want to offer a path to using open models that “just works”. One that will stay on the frontier, without you having to do a thing.
