Zhipu AI's flagship 744B MoE coding model with a solid 1M-token context, MIT open weights, dual thinking-effort modes, and long-horizon agentic performance at roughly 1/6 the price of GPT-5.5.

Anthropic's most intelligent model combining maximum capability with practical performance, featuring unique effort parameter control and exceptional long-horizon coding efficiency.

The world's best coding model and strongest agent builder, featuring state-of-the-art performance on software engineering benchmarks with 200k-1M token context window.

Minimal terminal coding harness that adapts to your workflows: four core tools, ~1k-token system prompt, TypeScript extensions, skills, session trees, 15+ providers, and four modes (TUI, print, RPC, SDK).

Next-gen AI code completion by Tabnine founder, featuring 1M token context window and blazing-fast response.

NVIDIA's QA-optimized reranking model with 32768 tokens ultra-long context support, Mistral-based architecture, TensorRT acceleration.

Enterprise-grade reranking model with 16000 tokens extended context support, optimized for RAG applications, available in standard and lite versions.