Pricing
Simple cost, pay for what you use.Start for freeExperiment with our API with $20 of free compute.
Pay as you goYou are billed per millisecond of compute.
ScalableAccess to scalable infrastructure, without the hassle of maintaining it.
Compute cost
$0.00055
per second
Choose a plan to start using Pipeline
Full access to our serverless APIChoose a plan to start using Pipeline
Full access to our serverless APIDeveloper plan
Developer plan
$12.99/mth
$12.99/mth
+ compute cost
Access to all our state-of-the-art pre-trained models
Unlimited API requests
Billed per millisecond of compute
Basic chat and email support
FREE for the first month and $20 of free compute
Enterprise plan
Enterprise plan
Everything in Developer plan
Custom Model deployment
Fine-tuning of models
Custom compute pricing
Dedicated support
How is cost calculated?
You’re billed only when a GPU is computing your requestHow is cost calculated?
You’re billed only when a GPU is computing your requestBillable
GPU active
- 1. API request sent
- 2. GPU starts processing request
- 3. GPU compute ends
- 4. API sends result
Example compute cost per model
Here are real-world examples of how much running a model will costExample compute cost per model
Here are real-world examples of how much running a model will costModelEstimated cost
GPT-J
$0.0222/ 1K tokens(~40s of compute)
GPT-2 Large
$0.0167/ 1K tokens(~30s of compute)
GPT-Neo 2.7B
$0.0267/ 1K tokens(~48s of compute)
DALL·E Mini
$0.0083/ 9 images(~15s of compute)
DALL·E Mega
$0.0133/ 9 images(~24s of compute)
Frequently asked questions
Frequently asked questions
What is the difference between a pipeline and a model?
A pipeline surrounds a model with inference logic so that your user's inputs and the model's raw outputs can be processed to produce the desired output. For example, the GPT-J pipeline adds input arguments and logit sampling techniques to the underlying GPT-J model within it.
What pipeline should I choose?
That depends on your task, but for text generation our best pipeline is GPT-J, and for image generation our best pipeline is DALL·E Mega. You can experiment with all our other pipelines too, or ask us for advice on which one to use.
Can I use your API for my own ML models?
Yes! We can deploy custom models and create a private endpoint so you can run on our serverless hardware. This functionality isn't yet available over the API, so send us a message and we'll discuss your needs and how we can serve them.
Some of my requests take longer than others, why?
It's rare that you'll experience changing inference times as long as your requests are identical. However this can happen on occasion when our proprietary task distribution software decides to route your task to different GPUs. We are always improving these algorithms.
Does your API have a cold-start issue?
Until bandwidth across PCIE into the GPU is instantaneous, all ML compute providers will be troubled by the cold-start issue where models first require loading before inference can be served. With our custom distribution software we have minimised the impact of these, and you will never be charged for model loading time.
What is a token in NLP?
ML models only deal with numbers, not words. So to convert a word to a number, you need to break it down into tokens. Different tokenizers use different strategies, but a token roughly corresponds to five characters of text content in our pipelines.