Inference subnets
Inference on Bittensor today
17 subnets are classified under inference. 13 publish at least one first-party interface and 17 have a surface that answered our most recent probe. The thing to compare here is not raw capacity but what the validator actually rewards: a subnet scoring answer quality and one scoring latency produce very different miner behaviour, and the API you end up calling reflects whichever it is. Check whether a specification exists before you plan an integration around it.
| Subnet | Readiness | Surfaces | Health |
|---|---|---|---|
| SN2 DSperse | 100 | 3/24 | |
| SN6 Numinous | 100 | 6/27 | |
| SN14 Cacheon | 100 | 4/25 | |
| SN53 engy | 100 | 5/16 | |
| SN59 Babelbit | 100 | 3/25 | |
| SN38 ChronoLLM | 96 | 4/25 | |
| SN64 Chutes | 96 | 19/76 | |
| SN96 Verathos | 96 | 7/69 | |
| SN110 Green Compute | 96 | 4/110 | |
| SN28 gm | 93 | 2/21 | |
| SN46 Instant | 93 | 3/51 | |
| SN10 Pareton | 86 | 3/12 | |
| SN29 hoτfloaτ | 86 | 6/15 | |
| SN92 Enclave | 86 | 0/13 | |
| SN27 Orion | 78 | 0/11 | |
| SN95 Actual | 74 | 0/12 | |
| SN31 rec4ll | 10 | 0/5 |
What "inference" means here
Subnets whose miners serve model output on demand — text, embeddings, classification or scoring — and whose validators grade that output rather than the hardware behind it.
How the classification is derived
Categories come from what a subnet publishes about itself — its declared purpose, its source repository and the interfaces it exposes — not from a hand-maintained list. A subnet can belong to several, and 60 of 129 currently belong to none, which is a coverage gap in our data rather than a statement about those subnets.