The Model Catalog.
One Unified API.

Z.ai's large-scale reasoning model with a 1M-token context window. OpenRouter lists it as text-only, reasoning-enabled, and highly ranked for code, websites, 3D, full-stack agents, and long-horizon software engineering.

Alibaba Qwen's dense 27B multimodal model. It accepts text, image, and video input, returns text, supports reasoning/tool parameters, and fits product analysis, visual understanding, and cost-controlled multimodal workflows.

DeepSeek's efficiency-optimized MoE model with 284B total parameters, 13B active parameters, and a 1M-token context window. Use it for fast inference, low-cost coding help, and high-throughput production workloads.

Moonshot AI's next-generation multimodal model for long-horizon coding, UI/UX generation, and multi-agent orchestration. It accepts text and image input with a 256K context window.

MiniMax's next-generation text reasoning model for autonomous productivity, structured analysis, and multi-agent workflows. OpenRouter marks reasoning as mandatory and lists a 200K-class context window.

Xiaomi's flagship text model for general agentic capability, complex software engineering, and long-horizon tasks. It supports a 1M-token context window and very large output budgets.