Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

myles-l

launchablesDecision modelOpen weights

myles-l by launchables is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text.

Pricing

No hosted price is listed. The weights are open: the cost is your own compute.

Specifications

Provider
launchables
Parameters
—
Released
Oct 2026
Open weights
Yes
Question types
Choice (one of N options), Score (ordered rubric), Yes / no
Mechanism
Decoder LM with a decision readout
Backbone
microsoft/phi-4
Jev-compatible request
No
Runs on CPU
—
License
myles-evaluation-licence
Hugging Face
launchables/myles-l

Compare myles-l with…

myles-l vs amos-1-large—/1M inmyles-l vs amos-1-medium—/1M inmyles-l vs Celeris-1 Decision$0.04/1M inmyles-l vs ScaleDown Classify-1$0.04/1M inmyles-l vs Cloudflare clef—/1M inmyles-l vs Cloudflare clef-flash—/1M in

FAQ

How much does myles-l cost?

myles-l has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can myles-l answer?

myles-l answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is myles-l well calibrated?

No calibration measurement for myles-l is recorded yet.

Is myles-l open weight, and can it run on a CPU?

Yes, myles-l has open weights.

Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.