Loading…
2 models tracked from DeepSeek.
DeepSeek's flagship V4 MoE model (1.6T total / 49B active params), released April 2026 — frontier reasoning, coding and agentic performance with a 1M-token context. Open weights.
DeepSeek's fast, economical V4 MoE model (284B total / 13B active params), released April 2026 — near-flagship benchmarks at a fraction of the cost, with a 1M-token context. Open weights.