Turn prompts into APIs instantly

Craft a prompt in code or in our UI and instantly get an API endpoint you can call. No need to deploy complex libraries (👀 LangChain), vector databases, or other tooling. Iterate on your prompts quickly and integrate instantly using a simple REST API.

Get startedLearn more 


import * as cadenai from 'cadenai';


cadenai.init({ apiKey: 'MY_KEY' })
const prompt = cadenai.createPrompt({
  prompt: `You are a marketing manager at a startup.
    Write an email to {name}
  `,
});


const response = cadenai.prompts.createCompletion(prompt, {
  name: 'Bob'
});

Features

Deploy production quality AI faster

Everything you need in one scalable, secure, and easy to use platform.

Prompt management
Create, edit, and manage prompts with a simple, intuitive interface. Test and iterate quickly with our built-in testing tool. Share prompts with your team and collaborate in real-time.
Fast and easy integration
Integrate once with your codebase and change models and prompts on the fly without re-deploying your code. Every prompt gets a simple to use REST API endpoint. Use it directly or install our JavaScript/TypeScript or Python libraries.
Connect your data
Enable your prompts to answer questions on your company-specific data, write in your style, and much more. Connect your data sources quickly and securely and use them in your prompts. The fastest and easiest way to leverage advanced techniques like Retrieval Augmented Generation (RAG).
Models for every use case
Get immediate access to all the latest commercial and open source models. Use our API key and only pay for what you use or bring your own key(s). Switch models at any time to optimize for performance and cost without code changes.
Logging and advanced analytics
Ensure your prompts are working as intended with your customers, spot hallucinations, and use live data to further refine and optimize. Full logging and analytics to track usage, errors, and more. Export your logs to your own data warehouse.
Low operational cost
No infrastructure to host or manage. API endpoints run on our servers and scale automatically. No need to worry about GPUs, CPUs, or RAM. We handle it all for you.

Pricing

Flexible plans that scale with you

All plans include 1000 requests/mo for free using open source models. Use our keys to access any model (OpenAI, Google, Cohere, etc.) and pay for usage or bring your own key(s).

Free

Start for free!

$0/month

Get started for free

Everything necessary to get started.

  • 100 requests/mo free (open source models)
  • Use our API key(s) or bring your own
  • Use any model and pay only for usage
  • 10K logs/mo for observability
  • Basic analytics
  • Unlimited users
  • 7 day log retention

Pro

$99/month

Sign up

Everything in Free, plus advanced analytics and data source connections

  • 1M logs/mo for observability
  • Data source connectors
  • Advanced analytics
  • 30 day log retention
  • 24-hour support response time

Enterprise

Custom

Contact us

Everything in Pro, plus collaboration tools and deeper insights.

  • Single sign-on (SSO)
  • Log export and flexible retention
  • Custom data sources
  • Direct database connections and peering
  • Customized support and consulting

Basic

GPT-3.5
Llama 2

Advanced

GPT-4
Mixtral 8x7B