Scira
Models published by Scira, available through the AnyRouter API. Each can route across multiple upstream providers for availability and price.
Amos 1 Large is an open-weight (Apache 2.0) decision model from Scira: a 27B decoder fine-tuned from Qwen3.8-27B and Scira's most capable decision model, for multi-step questions, long policies and trade-offs. Context 128K tokens; about 122 ms median server time. Send a state and typed questions (noul / choice / score) and get a calibrated probability per answer in one pass — not generated chat text. English only. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).
Amos 1 Medium is an open-weight (Apache 2.0) decision model from Scira: a 9B decoder fine-tuned from Qwen3.5-9B — fast and accurate, level with Large on typed decisions in about half the time. Context 128K tokens; about 61 ms median server time. Send a state and typed questions (noul / choice / score) and get a calibrated probability per answer in one pass — not generated chat text. English only. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).
Amos 1 Mini is an open-weight (Apache 2.0) decision model from Scira: a 0.5B encoder that answers every question in one pass on a CPU — simple decisions where the answer is in the case. Reads 9K tokens per pass; about 27 ms median server time. Send a state and typed questions (noul / choice / score) and get a calibrated probability per answer in one pass — not generated chat text. English only. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).
Amos 1 Small is an open-weight (Apache 2.0) decision model from Scira: a 2B decoder fine-tuned from Qwen3.5-2B, built for volume and for cases with photos. Context 256K tokens; about 48 ms median server time. Send a state and typed questions (noul / choice / score) and get a calibrated probability per answer in one pass — not generated chat text. English only. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).