A unified interface for LLMs

This is a cloaked model provided to the community to gather feedback. It’s a powerful, all-purpose model supporting long-context tasks, including code generation. All prompts and completions for this model are logged by the provider as well as OpenRouter.

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.

Ministral 8B is a state-of-the-art language model optimized for on-device and edge computing. Designed for efficiency in knowledge-intensive tasks, commonsense reasoning, and function-calling, it features a specialized interleaved sliding-window attention mechanism, enabling faster and more memory-efficient inference. Ministral 8B excels in local, low-latency applications such as offline translation, smart assistants, autonomous robotics, and local analytics.

The model supports up to 128k context length and can function as a performant intermediary in multi-step agentic workflows, efficiently handling tasks like input parsing, API calls, and task routing. It consistently outperforms comparable models like Mistral 7B across benchmarks, making it particularly suitable for compute-efficient, privacy-focused scenarios.