Tencent Hy4 Preview

Tencent Hy3

Hy3 is Tencent's 295B-parameter Mixture-of-Experts model with 21B active parameters, native 256K context, and configurable reasoning modes. It is built for coding, long-context comprehension, multi-turn dialogue, and agentic task execution with a focus on high-throughput production workloads.

DeepSeek V4 Flash 0423

The original 0423 checkpoint of DeepSeek V4 Flash, with a 1M-token context window, text input, tool calling, structured output, and optional reasoning.

DeepSeek V4 Flash 0423 (Thinking)

The original 0423 checkpoint of DeepSeek V4 Flash, with a 1M-token context window, text input, tool calling, structured output, and optional reasoning.

Mistral Large 4

Mistral Large 4 is an open-weight multimodal mixture-of-experts model with 1.05T total and 49B active parameters, built for reasoning, coding, tool use, and structured output. It supports a 512K-token context window.

Qwen 3.8 27B Antislop

Qwen 3.8 27B Antislop is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.

Qwen 3.8 27B DarkIdol

Qwen 3.8 27B DarkIdol is a creative finetune served by Aoru in NVFP4 with a 262,144-token context window. It supports image understanding, tool calling, and optional reasoning.