Sage S2.1 Flash
Sage S2.1 Flash is a released agents, vision, and json / tool use model with open-source; evaluate it while provider pricing coverage matures.
No tracked provider pricing is available yet.
No tracked provider pricing is available yet.
About
Sage S2.1 Flash is Shanghai AI Laboratory's scientific multimodal model, publicly documented by the maker on November 16, 2026. It combines scientific data understanding with retrieval, programming and tool use for research that requires repeated analysis and verification. Sage SciPerception encoders and projectors represent inputs such as molecular graphs, crystal structures, and protein sequences and structures alongside text. The model card explicitly licenses both code and model weights under MIT. Weights and deployment instructions are public.
Providers
No active provider routes are tracked for this model yet.
Capabilities
Benchmark peer barsfor Agents
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
internlm/Sage-S2.1-Flash