Tested and written up.
Added Apr 24, 2026
DeepSeek V4-Flash is the efficient sibling of V4-Pro, offering a 1M-token context window and configurable thinking modes at a fraction of the API cost. It is optimized for high-throughput chat, classification, bulk extraction, and agentic coding workloads, with a July 2026 update that boosted agent and coding benchmarks.
Why: V4-Flash delivers the same 1M context and thinking modes as V4-Pro at roughly one-third the API cost, making it the practical default for most production workloads.
Added Apr 22, 2026
Open-weight preview of Hunyuan 3 (Hy3), a 295B-parameter MoE model with 21B active parameters and a 262K context window. Supports reasoning, function calling, and tool use, and is available via OpenRouter and Tencent Cloud TI Platform.
Why: Tencent's strongest open-source Hunyuan model to date, with competitive coding and agentic benchmarks.
Added Apr 21, 2026
Kimi K2.6 is Moonshot AI's open-weight multimodal model released April 21, 2026. It supports text, image, and video input, thinking and non-thinking modes, and a 256K context window, with improved long-context coding stability and agent-task performance.
Why: Kimi K2.6 improves on K2.5 with stronger long-context coding and is a practical open-weight alternative for teams that want multimodal agents without the cost of closed frontier models.