Tokens API

Tokens API

Input token counts and costs for over 160 AI models

8 followers

A free service and API to get input token counts and costs for over 160 AI models. Get your API key and start integrating our Tokens API into your AI apps and workflows. Useful for checking inputs for context window size and monitoring your AI usage budget.
Tokens API gallery image
Tokens API gallery image
Tokens API gallery image
Free
Launch Team / Built With
Intercom
Intercom
Startups get 90% off Intercom + 1 year of Fin AI Agent free
Promoted

What do you think? …

Dave Donaldson
Maker
📌
Hello Product Hunters! I'm excited to announce the launch of the first product for Zatomic AI: our Tokens API. Tokens are the foundation of generative AI models, and token usage is how we all get charged when we use them. But there's a gap: we don't get to know how many input tokens we're using until *after* we've called the AI model. For any maker out there building AI apps, this is an issue when you need to consider context windows and AI budget constraints. At Zatomic AI, we have a need to get input token counts for a number of other things we're working on, so when I went looking for how to get them, all I found were a couple libraries and client-side browser apps. Nothing with an API where you can send inputs and model names and get the token counts (and their cost, if applicable). In a world powered by APIs, and considering we all use AI models through their APIs, this felt like something every AI maker could benefit from. That's where our Tokens API comes in. It allows anyone using AI models to easily integrate input token counts and costs into their AI apps and workflows. Every maker and company building apps and services with generative AI needs something like this. The Tokens API currently supports 165 AI models from a wide variety of model families, including: ✔️ AI21 Jamba ✔️ Amazon Titan ✔️ Anthropic Claude ✔️ Cohere Command R ✔️ Databricks Dolly ✔️ DeepSeek ✔️ Google Gemini and Gemma ✔️ IBM Granite ✔️ Meta Llama ✔️ Microsoft Phi-3 ✔️ Mistral ✔️ Nvidia ✔️ OpenAI GPT and Text Embedding ✔️ Qwen ✔️ Snowflake Arctic ✔️ Stability AI ✔️ TIIUAE Falcon ✔️ xAI Grok ✔️ Zyphra Zamba You can view the entire list and specific models here. And to make the barrier-to-entry as low as possible, we're giving this away for free, for everyone. All that's required is a quick signup with your name and email so that you can get an API key. That's it. No credit card, no payment, no up-front marketing survey. While we have much more to come at Zatomic AI, we're extremely interested in your feedback about the Tokens API and other things you'd like to see done with it. Just let us know in the comments or send an email to hello@zatomic.ai. We're excited to see what you do with it.