Pricing

Leveling up AI collaboration and compute

Users and organizations already use the Hub as a collaboration platform,we’re making it easy to seamlessly and scalably launch ML compute directly from the Hub.

HF Hub

Collaborate machine Learning

1000/mo Fast Inference credits
Ability to price your custom models highers
Spotlight your custom models on Featured page
Nesa Pro Badge

Forever

Free

Nesa

PRO

Unlimited Access

1000/mo Fast Inference credits
Ability to price your custom models highers
Spotlight your custom models on Featured page
Nesa Pro Badge

Subscribe for

/month

Nesa for enterprise

Accelerate your AI Roadmap

SSO and SAML support
Select data location with Storage Regions
Precise actions reviews with Audit logs
Granular access control with Resource groups
Managed billing with yearly commits
Priority support

Starting at

per user / month

API Pricing

Simple and flexible.
Only pay for what you use

Contact Sales

Spatial Transcriptomics

Name	input price ($)	output price ($)
GraphST	0.030/ input (AnnData)	0.315 / output (Clusters)
TISSUE	0.050 / input (AnnData)	0.500 / output (Regions)
CCST	0.033 / input (AnnData)	0.300 / output (Clusters)

Structual Bioinformatics

Name	input price ($)	output price ($)
ing Alpha fold	0.032 / input (Sequence)	0.125 / output (Structure)
RoseTTAFold	0.035 / Input (Sequence)	0.150 / Output (Structure)
OpenFold	0.028 / Input (Sequence)	0.120 / Output (Structure)

Metabolic Modeling

Name	input price ($)	output price ($)
single cell flux estimation analysis (scFEA)	0.014 / input (Expression Matrix)	0.190/output (Fluxes Matrix)
single-cell Flux Balance Analysis (scFBA)	0.015/ input (Expression Matrix)	0.130/output (Fluxes Matrix)
FLUXestimator	0.015/ input (Expression Matrix)	0.150/output (Fluxes Matrix)

System Biology

Name	input price ($)	output price ($)
Compositional Perturbation Autoencoder	0.030/input (Expression Matrix)	0.145/ output (Expression Matrix)
ChemCPA	0.035/input (Expression Matrix)	0.145/ output (Expression Matrix)
Graph Variational Causal Inference (GraphVCI)	0.015/input (Expression Matrix)	0.100 / output (Expression Matrix)

Image Super resolution

Name	input price ($)	output price ($)
FaceUp Sharp	-	0.003 / Image (2x)
Universal Upscaler	-	0.002 / Image (4x)
Nomos ESR-GANs	-	0.0015 / Image (4x)

Depth Estimation

Name	input price ($)	output price ($)
depth-anything/Depth-Anything-V2-Large	-	0.015 / Image
Intel/dpt-large	-	0.011 / Image
apple/DepthPro	-	0.009 / Image

Image segmentation

Name	input price ($)	output price ($)
briaai/RMBG-1.4	-	0.0042 / Image
facebook/detr-resnet-50-panoptic	-	0.0030 / Image
apple/deeplabv3-mobilevit-small	-	0.0014 / Image

Object Detection

Name	input price ($)	output price ($)
facebook/detr-resnet-50	-	0.00015/ Image
microsoft/table-transformer-detection	-	0.00015/ Image
hustvl/yolos-base	-	0.0004/ Image

Unconditional image generation

Name	input price ($)	output price ($)
google/ddpm-celebahq-256	-	0.00025/ Image
deepsynthbody/deepfake_ecg	-	0.00035/ Image
commaai/commavq-gpt2m	-	0.00035/ Image

Image classification

Name	input price ($)	output price ($)
microsoft/resnet-50	0.004/image	0.00010/ output (labels and confidence scores)
AdamCodd/vit-base-nsfw-detector	0.003/image	0.00025/output (labels and confidence scores)
trpakov/vit-face-expression	0.005/image	0.00050/output (labels and confidence scores)

Feature extraction

Name	input price ($)	output price ($)
facebook/dinov2-base	0.005 / image	0.012 / output (Tensor)
nomic-ai/nomic-embed-vision-v1.5	0.007 / image	0.020 / output (Tensor)
microsoft/rad-dino-maira-2	0.006 / image	0.018 / output (Tensor)

Text-to-speech

Name	input price ($)	output price ($)
OuteAI/OuteTTS-0.1-350M	0.05/ 1M Token	0.0035 / output (30 sec Audio)
suno/bark	0.060 / 1M Token	0.0050 / output(30 sec Audio)
SWivid/F5-TTS	0.075 / 1M Token	0.0055/ output (30 sec Audio)

Automatic Speech Recognition

Name	input price ($)	output price ($)
openai/whisper-large-v3-turbo	0.0035 / input (30 sec Audio)	0.40 / 1M Token
facebook/wav2vec2-base-960h	0.0015 / input (30 sec Audio)	0.20 / 1M Token
openai/whisper-large-v3	0.0015 / input (30 sec Audio)	0.20/ 1M Token

Audio Classification

Name	input price ($)	output price ($)
MIT/ast-finetuned-audioset-10-10-0.4593	0.0155/ input (30 sec Audio)	0.00042 / output (labels and confidence scores)
superb/hubert-base-superb-er	0.045/ input (30 sec Audio)	0.00060 / output (labels and confidence scores)
m-a-p/MERT-v1-330M	0.050 / input (30 sec Audio)	0.000070/ output (labels and confidence scores)

Speech-to-Text

Name	input price ($)	output price ($)
espnet/xeus	0.055 / Input (30 sec Audio)	0.250 / 1M Token
UsefulSensors/moonshine-base	0.090 / input (30 sec Audio)	0.350 / 1M Token
eesungkim/stt_kr_conformer_transducer_large	0.030 / Input (30 sec Audio)	0.200 / 1M Token

Character Recognition OCR

Name	input price ($)	output price ($)
microsoft/OmniParser	0.035 / Image	0.002 / 1M Token
yifeihu/TB-OCR-preview-0.1	0.050 / Image	0.005 / 1M Token
faisalraza/layoutlm-invoices	0.025 / Image	0.003 / 1M Token

Text Classification

Name	input price ($)	output price ($)
SamLowe/roberta-base-go_emotions	0.005 / 1M Token	0.00004 / output (labels and confidence score)
ProsusAI/finbert	0.006 / 1M Token	0.00005 / output (labels and confidence score)
RLHFlow/ArmoRM-Llama3-8B-v0.1	0.058 / 1M Token	0.0005 / output (labels and confidence score)

Sentiment analysis

Name	input price ($)	output price ($)
cardiffnlp/twitter-roberta-base-sentiment-latest	0.009 / 1M Token	0.00004 / output (labels and confidence score)
mrm8488/distilroberta-finetuned-financial-news	0.005 / 1M Token	0.00005 / output (labels and confidence score)
unitary/toxic-bert	0.008 / 1M Token	0.00005 / output (labels and confidence score)

Named Entity Recognition

Name	input price ($)	output price ($)
mdarhri00/named-entity-recognition	0.045 / 1M Tokens	0.070 / 1M Token
blaze999/Medical-NER	0.025 / 1M Tokens	0.045 / 1M Tokens
dslim/bert-base-NER	0.050 / 1M Tokens	0.065 / 1M Tokens

Machine Translation

Name	input price ($)	output price ($)
google-t5/t5-base	0.019/ 1M Tokens	0.039/ 1M Tokens
Helsinki-NLP/opus-mt-ar-en	0.012/ 1M Tokens	0.035/ 1M Tokens
google-t5/t5-large	0.031/ 1M Tokens	0.038/ 1M Tokens

Question-answering

Name	input price ($)	output price ($)
MaRiOrOsSi/t5-base-finetuned-question-answering	0.003 / 1M Tokens	0.0001 / output (answer and indices)
distilbert/distilbert-base-cased-distilled-squad	0.005/ 1M Tokens	0.003 / output (answer and indices)
tinyroberta-squad2	0.008/ 1M Tokens	0.006 / output (answer and indices)

Content Summarization

Name	input price ($)	output price ($)
facebook/bart-large-cnn	0.0021 / 1M Tokens	0.031 / 1M Tokens
Falconsai/medical_summarization	0.0029 / 1M Tokens	0.0035 / 1M Tokens
google/pegasus-newsroom	0.0027 / 1M Tokens	0.0034 / 1M Tokens

Sentence-similarity

Name	input price ($)	output price ($)
sentence-transformers/all-MiniLM-L6-v2	0.035 / 1M Tokens	0.002 / output (Tensor)
BAAI/bge-m3	0.0029 / 1M Tokens	0.0035 / 1M Tokens
sentence-transformers/all-mpnet-base-v2	0.029/ 1M Tokens	0.001 / output (Tensor)

Time series forecasting

Name	input price ($)	output price ($)
Transformers	0.004 / Input (tabular)	0.009 / output (tabular)
FbProphet	0.003 / Input (tabular)	0.003 / output (tabular)
Sarimax	0.003 / Input(tabular)	0.002 / output (tabular)

Text-generation

Name	input price ($)	output price ($)
Llama-3.2-1B-Instruct	0.015 / 1M Tokens	0.125 / 1M Tokens
Llama-3.2-3B-Instruct	0.031 / 1M Tokens	0.258 / 1M Tokens
Llama-3-8B-Lexi-Uncensored	0.058 / 1M Tokens	0.489 / 1M Tokens

Centralized models

Name	input price ($)	output price ($)
gpt-4-turbo-preview	9.211 / 1M Tokens	29.260 / 1M Tokens
gpt-4o	1.156 / 1M Tokens	9.885 / 1M Tokens
dall-e-3	-	0.078 / Image (1024 * 1024)

Image-generation

Name	input price ($)	output price ($)
FLUX.1-schnell	0.500 / 1M Tokens	0.005 / Image (1024 * 1024)
LazyMix-Uncensored	0.188 / 1M Tokens	0.002 / Image (1024 * 1024)
holodayo-xl-2.1	0.391 / 1M Tokens	0.003 / Image (1024 * 1024)

Text-to-video

Name	input price ($)	output price ($)
Realistic_Vision_V6.0_B1_noVAE_8	0.500 / 1M Tokens	0.025 / Video (1024 x 1024)
THUDM/CogVideoX-5b	0.650 / 1M Tokens	0.090 / Video (720 x 480)
Animated DreamShaper_8-steps	0.350 / 1M Tokens	0.070 / Video (1024 x 1024)

Frequently asked questions

⁰¹How does nesa scale?

Nesa scales large model inference by facilitating it off chain, so that the system can benefit from the efficiency of nodes utilizing advanced hardware and various software optimization techniques not possible in smart contracts. This off-chain inference process is secured by our proprietary cryptography solution of the commit and reveal paradigm, and is further managed through dynamic hardware spec mandates for trusted nodes in the system. This safely increases Nesa's query throughput as more transaction requests are made and more nodes join the network.

⁰²What is Nesa's architecture?

Nesa is designed to deconstruct the model evolution and querying process and compartmentalize each component. Information and instructions integral to the inference query are containerized on-chain, heavy datastores are bridged off-chain, AI models are hosted in decentralized storage, and query responses are reported back to the chain from trusted nodes via Nesa oracles posting transaction data.

⁰³What programming languages and VMs are supported by Nesa?

Because of Nesa’s modular architecture, it can support any programming language or VM. Currently supported languages include Solidity (EVM), Rust & Golang (Cosmos SDK).

⁰⁴How do I run a node on Nesa?

Nesa supports multiple testnets that users can run nodes on in preparation for mainnet. Information on running testnet nodes is available in our docs.

⁰⁵Where can developers get started?

Developers can head to the docs to get started with building on Nesa.

⁰⁶How are queries paid for?

Nesa is designed to have a token used to secure the network via Proof of Stake and to pay for transaction fees on the network for inference queries, called PayForQuery transactions.

Build on Nesa as a developer, stake NES to mine.

Start building on Nesa by uploading your model container and bringing a node online.

Build on Nesa

Mine on Nesa