Amos 1 large
Amos 1 large is a 27B decision model that answers typed questions with probabilities for each allowed answer, without generating free-form text. It accepts text, JSON, or photos and is available through a hosted API or for self-hosting with its published weights and serving package.
What it does
Use it to make structured decisions from cases such as customer requests, policies, or images, including selecting answers, extracting quotes, and identifying regions.
- Availability
- Hosted API with no key; model download and serving package provided
- Pricing model
- Not established
- Deployment
- Hosted or run yourself; 80 GB GPU
- Privacy
- Not established
- Licence
- Apache-2.0
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
5 claims- The model accepts cases as text, JSON, or a photo and answers typed questions with probabilities for allowed answers. [1]
Give it a case (text, JSON or a photo) and a schema of typed questions; it answers every
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Question types include yes/no, pick one, rate, pick any, quote, and point. [1]
Question types: yes/no (`noul`), pick one (`choice`, up to 255 options), rate (`score`), pick any (`multi`), quote
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - A hosted endpoint is available at https://api.amos.scira.ai/v1/systemone without a key. [1]
Hosted, no key: `POST https://api.amos.scira.ai/v1/systemone` with `"model": "amos-1-large"`.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model can be run locally using the provided serving package and runs on an 80 GB GPU. [1]
- The model reads up to 131,072 tokens per request. [1]
131,072 tokens per request.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
Hugging FaceOwner-controlled
https://huggingface.co/mukaddamzaid/amos-1-large
Retrieved 2026-10-28 00:39 UTC
Verified
Versions
2| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 2 | 2026-10-15 09:21 UTC | material change | access, pricing, availability, deployment | Current |
| 1 | 2026-10-14 10:20 UTC | publication | None | Current |
In briefs
1- Extract structured text from PDFs and images on a CPU Daily brief 2026-10-14
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.