Models Overview
SAGEA develops open-weight and commercial models for language, speech, and document understanding. Explore the full lineup, compare capabilities, and find the right model for your use case.
Featured Models
SAGE 2.4 Actus
PREMIEROur frontier-class multimodal model optimized for agentic and coding use cases.
v26.04
SAGE 2.5 Celer
PREMIERHybrid model unifying instruct, reasoning, and coding in a single efficient model.
v26.05
SAGE OSS
OPENOpen-source model collection optimized for community research and development.
v26.03
Sonus TTS
PREMIERState-of-the-art TTS with zero-shot voice cloning and multilingual support.
v26.03All models
A list of all available models, helping you explore their capabilities, performance, trade-offs, and more.
Generalist models
Text and multimodal models for broad reasoning, coding, tool use, and agentic tasks.
SAGE 2.4 Actus
PREMIEROur frontier-class multimodal model optimized for agentic and coding use cases.
v26.04SAGE 2.5 Celer
PREMIERHybrid model unifying instruct, reasoning, and coding in a single efficient model.
v26.05SAGE OSS
OPENOpen-source model collection optimized for community research and development.
v26.03Audio models
Models for speech synthesis, voice cloning, and real-time transcription. Base URL: https://api.sagea.space/v1.
OCR models
Models for document understanding, text extraction, and structured OCR outputs.
