SEA-LION Guard v2 E4B
SEA-LION Guard v2 E4B is available now for long context and classification with open-source and 128K context; evaluate it while provider pricing coverage matures.
No tracked provider pricing is available yet.
About
SEA-LION Guard v2 E4B is AI Singapore's Southeast Asian safety and agent-governance model, fine-tuned from Gemma 4 E4B IT as a decision model: instead of free text it returns probabilities for content moderation (safe / sensitive / unsafe), rule applicability and rule violation under user-defined policies, across multi-turn conversations and tool calls in 8 languages (Burmese, English, Filipino, Indonesian, Malay, Tamil, Thai, Vietnamese). MIT license.
Providers
No active provider routes are tracked for this model yet.
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Long context
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
No tracked provider pricing is available yet.