SpaCy models in production

We serve your spaCy custom models, and all the pre-trained models, through a RESTful API. Deploy your NLP projects to production in no time. No DevOps required.

High Performance

Fast and responsive spaCy models suited for Natural Language Processing in production


Upload your own trained models and let us serve them for you

No Complexity

Do not worry about DevOps or API programming and focus on NLP only

Pre-trained Models

All the spaCy pre-trained models are available: all languages and all sizes


Machine Learning models require a lot of resources to run properly with no downtime.

Clean API

Simple and well-documented API with client libs that make integration a breeze


In the example below, we apply Named Entity Recognition (NER) to a sentence, by first using the en_core_web_sm spaCy model.

Then we are doing the same by using our custom spaCy model.

Client libraries are available in Python, Ruby, Go, Node.js, and PHP (more to come).


# Perform NER using spaCy's en_core_web_sm model:
curl" \
    -H "Authorization: Token 4eC39HqLyjWDarjtT1zdp7dc" \
    -X POST \
    -d '{"text":"John Doe is a Go Developer at Google"}'

# OR:

# Perform NER using your own custom model:
curl" \
    -H "Authorization: Token 4eC39HqLyjWDarjtT1zdp7dc" \
    -X POST \
    -d '{"text":"John Doe is a Go Developer at Google"}'


        "end": 8,
        "start":  0,
        "text": "John Doe",
        "type": "PERSON"
        "end":  25,
        "start":  13,
        "text": "Go Developer",
        "type": "POSITION"
        "end":  35,
        "start":  30,
        "text": "Google",
        "type": "ORG"

Other endpoints are also available for your Natural Language Processing projects like part of speech (POS) tagging and dependency parsing.

Many more pre-trained models are also available (all of them actually).

See the documentation for more details


Integrate your Own Models

Upload your own NLP custom models from your dashboard and use them straight away in production without worrying about deployment considerations like RAM usage, high-availability, scalability... You can upload and deploy as many models as you want to production.



If you already have an account, send us a message from your dashboard.

Otherwise, send us an email here: [email protected].

Deliver Your NLP Projects For Good

A lot of NLP projects are failing because shipping the models to production is harder than expected...

"We spent a lot of energy fine-tuning our machine learning models, but we clearly underestimated the go-live process. NLP Cloud saved us a lot of time!"

Patrick, CTO at MatchMaker

"Simple and efficient. Typically the kind of out-of-the box service that will make spaCy even more popular."

Marc, Software Engineer

"We did the maths: developing the API by ourself, and then creating and maintaining the production platform for our entity extraction models, would have taken around 2 months of work. Finally we did the same thing in 1 hour for a very fair price by using NLP Cloud."

John, CTO

"We had developed a working API deployed with Docker for our model, but we quickly faced performance and scalability issues. After spending weeks on this we eventually went for this cloud solution and we haven't regretted it so far!"

Maria, CSO at CybelAI

"None of us here really had the DevOps skills required to set up a robust production infrastructure for our Natural Language Processing projects. Doing this by ourselves would have taken months..."

Whalid, Lead Dev at Direct IT

"The NLP Cloud API has been extremely reliable and the support team is very nice and reactive."

Bogdan, Data Scientist at
Match Maker
Direct IT
Red Leaf Estate