Inside DaniLabs (SN2): The Bittensor Subnet Focused on Speed, Cost Goals, and Privacy

Imagine using an AI assistant that responds quickly, costs less to run, and does not retain your prompts after processing them. For developers building AI-powered applications, these are practical needs that can influence how much their products cost and how users trust them.

DaniLabs (SN2) is working toward this kind of infrastructure on Bittensor. Its goal is to distribute AI inference across a network of miners, allowing applications to access model responses while prioritizing speed, low costs, and data privacy.

The subnet is still in active development, but its validator infrastructure is already running as the team works toward launching its broader inference service.

What Is DaniLabs?

DaniLabs stands for Distributed Accelerated Neural Intelligence. It is a Bittensor subnet focused on building a distributed AI inference network, with the tagline “Intelligence, distributed.”

The project aims to make AI inference more accessible by allowing developers and applications to send requests to the network and receive responses from models running across distributed compute providers.

Its three core priorities are:

1) No data retention: Prompts and responses are processed without being stored after a request.

2) Speed: Reduce the time users wait for a usable response, including time to first token and overall generation speed.

3) Low cost: Make AI inference more affordable so developers can integrate useful AI features into everyday applications and standard plans.

These priorities shape the service DaniLabs is developing. The team has already recorded more than 22,000 requests during its early testing and has been speaking with potential customers who are routing inference workloads through the network.

We’re building AI inference on Bittensor. So far, we’ve recorded over 22,000 requests.

Take a look at the usage behind that number.https://t.co/qH3GWygNWW pic.twitter.com/GQRbH771nF

— DaniLabs (@danilabsai) November 11, 2026

From DSperse to DaniLabs

DaniLabs did not begin with a completely new subnet. Subnet 2 previously operated as DSperse under Inference Labs, where the focus was on zero-knowledge machine learning and cryptographic proofs that verified AI computations.

That work generated billions of proofs through developer and community activity. In mid-October 2026, Inference Labs handed the subnet over to DaniLabs, led by Dan Ivanov, known as @opendansor, who had contributed to scaling the previous project.

≫ See our earlier coverage on this transition, HERE.

How DaniLabs Works

DaniLabs follows Bittensor’s standard miner-validator structure on Subnet 2 (Netuid 2).

Miners provide the compute resources that run AI models and generate responses to inference requests while validators assess miner performance and submit on-chain weights, which determine how subnet emissions are distributed.

The validator system evaluates several operational metrics:

a) Decode speed: How quickly a miner generates tokens, with this metric weighted heavily.

b) Time to first token: How long it takes for a response to begin.

c) Completion reliability: Whether inference requests complete successfully.

d) Gateway-to-miner latency: The round-trip time between the service gateway and a miner.

The validator code is publicly available in the DaniLabs subnet GitHub repository. It verifies signed performance reports from miners against finalized chain state, helping ensure that reported measurements can be checked.

What Comes Next for DaniLabs?

DaniLabs is still early in its development. Its validator infrastructure is running, performance scoring is being tested, and the team is measuring usage while preparing the inference service and miner software.

The next key steps include activating performance-based rewards, releasing the Miner Kit, expanding technical documentation, and opening the inference service to more developers and users.

For Bittensor, DaniLabs represents a move toward distributed AI infrastructure that applications can use directly. Its progress will depend on whether the network can deliver reliable inference at competitive speeds and costs while maintaining its stated privacy approach.

≫ To fully understand subnets, miners, validators, or alpha tokens, see our earlier coverage, HERE.