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

Orca-4B-flash

roskosmos19Decision modelOpen weights

Orca-4B-flash by roskosmos19 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
roskosmos19
Parameters
5B
Released
Sep 2026
Open weights
Yes
Question types
Choice (one of N options), Score (ordered rubric), Yes / no
Mechanism
Decoder LM with a decision readout
Backbone
—
Jev-compatible request
Yes
Runs on CPU
No
License
apache-2.0
Hugging Face
roskosmos19/Orca-4B-flash

Compare Orca-4B-flash with…

Orca-4B-flash vs amos-1-large—/1M inOrca-4B-flash vs amos-1-medium—/1M inOrca-4B-flash vs Celeris-1 Decision$0.04/1M inOrca-4B-flash vs ScaleDown Classify-1$0.04/1M inOrca-4B-flash vs Cloudflare clef—/1M inOrca-4B-flash vs Cloudflare clef-flash—/1M in

FAQ

How much does Orca-4B-flash cost?

Orca-4B-flash has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can Orca-4B-flash answer?

Orca-4B-flash answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is Orca-4B-flash well calibrated?

No calibration measurement for Orca-4B-flash is recorded yet.

Is Orca-4B-flash open weight, and can it run on a CPU?

Yes, Orca-4B-flash has open weights. It needs a GPU to run at useful speed.

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.