Access our models directly through our API and pay for what you use, or deploy on Amazon SageMaker.
Get free, rate-limited usage for learning and prototyping. Usage is free until you go into production
Power your business with hosted language models.
Price per embedding
Price / Unit
$1.0 / 1000 embeddings
$2.0 / 1000 embeddings
If you require dedicated model instances, dedicated support channels, or custom deployment options, get in touch with our sales team
"Cohere excels at delivering high quality, low-latency language AI models and really supporting them. Having Cohere's team as an extension of ours lets us go 10x faster."
When an account is created, we automatically create an Trial API key for you. This API key will be available on the dashboard for you to copy, as well as in the dashboard section called “API Keys.”
To get a Production key, you'll need to have Owner privileges (or ask your organization Owner to complete the following steps). Navigate to the Billing and Usage page in your Cohere dashboard. Click on the Get Your Production key button and fill out the Go to Production workflow.
A Trial API key has a rate limit of 5000 generation units per month for Generate endpoint, 50 calls per month for summarize endpoint, and the embed and classify endpoint are rate limited at 100 calls / minute. A Production API key has a rate limit of 10,000 calls per minute. API calls made from a Trial API key are free. API calls made from a Production API key will be charged on a pay-as-you-go basis. Trial keys are not permitted to be used for production or commercial purposes.
Every account begins as a personal account and only has access to Trial API keys. As a personal account, you will not be able to add other members until you become part of an organization.
At Cohere, an organization is a group of personal accounts that share a singular billing portal. Organizations are not automatically given Production API key access, and a member of the organization must still fill out our application form for production access. Personal accounts cannot share billing information with other accounts.
Your model selection reflects your relative prioritization of model performance and speed. Larger models offer better performance and are capable of more complex tasks, while smaller models have faster response times.
API calls made from a Trial API key will be free. API calls made from a Production key will be billed on a pay-as-you-go basis. Your bill will be issued at the end of every calendar month.