Get access to the Cohere Platform

Cohere trains massive language models and puts them behind a simple API. We handle the complexities of collecting massive amounts of text data, evolving neural network architectures, distributed training, and serving models around the clock.

Billions of parameters on tap

Cohere offers three baseline models, each with different amounts of power (i.e., parameters): small, medium, and large. Our Embed and Generate endpoints can be used to implement these models across a variety of different tasks.

Powerful

Our models gain a rich understanding of language and the world by reading text across billions of web pages.

Customizable

Finetune our models to improve performance on downstream tasks or teach the model large quantities of information that cannot be extracted with few-shot learning or prompt engineering.

Multi-purpose

Access language generation and model representations under one API.

Easy access

We handle of the complexities of collecting massive amounts of text data, architectures, distributed training, and serving models around the clock.

Embed

Return textual embeddings that capture semantic information about text.

import cohere
co = cohere.CohereClient('YOUR_API_KEY')
emb = co.embed(
model='baseline-small',
texts=['This album is not that great.', 'Their old stuff was better.'])
if emotion_classifier.predict(emb) < 0.5:
print('They did not like it')

Generate

Produce realistic text conditioned on a given input across a variety of tasks.

import cohere
co = cohere.CohereClient('YOUR_API_KEY')
predictions = co.generate(
model='baseline-medium',
prompt='Rephrase the following sentence:\n'
'1. When does the show start?\n'
'2. What time is the concert?\n'
'3. When is the beginning of the set?\n',
num_tokens=50)

Get access to the Cohere Platform

Sign up for free today and use the Cohere Platform to build natural language understanding and generation into your product with just a few lines of code.

Deploy language models with billions of parameters