MoonMath Zro (BYOK)BYOK

DeepSeek V4.1 Flash is the open-weight, cost-efficient sparse mixture-of-experts tier of the V4.1 family. It has 552B total parameters with 8B active on input and 16B on output, 1M context, and native vision in with text out. This is the original September 2026 checkpoint.

Dolly 1 Security is MoonMath's uncensored security variant of GLM-5.3 Flash for defensive and red-team workflows. It has no standard safety filters, so use it only on your own systems or ones you are authorized to test. It has a 1M-token context, 64K max output and text and image input. The acceptable-use policy still applies to every request.

Dolly 2 Security is MoonMath's uncensored variant of GLM-5.3 for defensive and red-team workflows. It has no standard safety filters, so use it only on your own systems or ones you are authorized to test. It has a 1M-token context, 131K max output and text-only input. The acceptable-use policy still applies to every request.

GLM-5.3 is Z.AI's open-weight reasoning model for coding and agentic workflows. It targets complex software engineering, long-running agents, and vulnerability analysis. It uses the same base model as GLM-5.2 with scaled post-training for stronger coding and token efficiency.