# Legacy Subnet 1 Apex ## What is Subnet 1? **Subnet 1** is Bittensor’s flagship subnet, focused on building **state-of-the-art open-source intelligence** through decentralized competitions and cutting-edge LLM research. Bittensor requires persistent research and innovation to compete with leading proprietary models for it to continue being a viable solution to closed-source and centralized alternatives.
## Core Goals * Produce agentic workflows with LLMs that surpass the capabilities of proprietary models at specific tasks. * Develop advanced inference techniques like **response ensembling** and **chain-of-thought reasoning**. * Prove that decentralized systems can produce **SOTA AI models**. * Serve as **Bittensor’s main entry point** for new users. * Power smart interfaces to interact with other subnets and digital tools. ## Why SN1 Matters With a long-standing legacy in the ecosystem, SN1 has led the way in **LLM-based incentive design**. It was rebuilt in January 2024 to take full advantage of the latest breakthroughs in LLM research and infrastructure. One of SN1’s biggest innovations is the development of **agentic workflows** — LLM-powered agents equipped with tools like API access, code execution, and web search. These workflows dramatically improve performance by reducing hallucinations, boosting accuracy, and enabling deeper, more reasoned outputs. Subnet 1 enhances the Bittensor environment by: * Creating an [arena for miners ](https://www.macrocosmos.ai/sn1/dashboard)to relentlessly build innovative agents designed to compete with proprietary models. * Producing highly specialised, targeted intelligence as a digital commodity for users. * Providing chat interfaces, APIs, and other mechanisms for users and businesses to interact with the intelligent hivemind. At present, subnet 1 powers multiple user-facing products, one of which being [Apex](https://docs.macrocosmos.ai/product-and-services/apex), part of our Constellation platform. * Subnet 1 additionally allows Validators to spin up their own api endpoints with 1 line, using OpenAI standard endpoints for seamless streaming to front-ends and plug-ins. * Expanding Bittensor's incentive landscape and framework, building on its legacy as the protocol's flagship subnet, and continuing to push the boundaries of mechanism design. ## Interoperability Subnet 1 works closely with other subnets to expand its capabilities: * subnet 13, Data Universe, through data annotation and sentiment analysis, * subnet 19, Inference, offloading tasks to an inference-specific subnet. ## Apex Client - Macrocosmos SDK **(SN1)** runs open-source language models like LLaMA and Mistral, and you can interact with it easily using the [readme](https://docs.macrocosmos.ai/developers/readme "mention")\ With the `ApexClient`, you can send prompts, run chat completions, and perform live web searches — all decentralized and miner-powered.\\ **You'll also need an API key. Visit** [api-documentation](https://docs.macrocosmos.ai/developers/api-documentation "mention") to get started. #### TLDR Subnet 1 plays a key role in Bittensor’s mission to compete with closed-source models by focusing on **specialization, innovation, and usability**. It strikes a balance between **research** and real-world **productization**, advancing the application of decentralized AI. Check out [Subnet 1's Dashboard](https://www.macrocosmos.ai/sn1/dashboard) for a variety of metrics for the competition and the model's performance quality. For more details about the subnet 1 R\&D work, take a look at our Substack articles: * [Chain-of-thought: SN1 enhanced with multi-step reasoning](https://macrocosmosai.substack.com/p/chain-of-thought-sn1-enhanced-with) * [Mixture-of-Miners: improving SN1’s performance](https://macrocosmosai.substack.com/p/mixture-of-miners-improving-sn1s) * [Introducing SN1’s dashboard: benchmarks, leaderboards, & miner stats](https://macrocosmosai.substack.com/p/introducing-sn1s-dashboard) * [Task management: Redesigning SN1’s validation mechanisms](https://macrocosmosai.substack.com/p/task-management-redesigning-sn1s) **Related resources** * [Website](https://www.macrocosmos.ai/sn1) * [Dashboard](https://www.macrocosmos.ai/sn1/dashboard) * [GitHub](https://macrocosmosai.substack.com/t/language-models) * [Substack](https://macrocosmosai.substack.com/t/language-models) * [Bittensor Discord](https://discord.com/channels/799672011265015819/1161764867166961704) * [Macrocosmos Discord](https://discord.com/channels/1238450997848707082) * [Cosmonauts - Macrocosmos Telegram](https://t.me/macrocosmosai) * [Macrocosmos X](https://x.com/MacrocosmosAI)