Quora's AI platform POE announced on Thursday that it will release an API that will allow developers to easily access different models or bots for their own applications.
There is no additional fee for the API. Instead, usage is tracked through the POE's existing point-based subscription plan. There, each model call costs the number of points set. For example, low quality image generation via GPT-4o with a 1:1 aspect ratio and 1024 x 1024 size cost 328 points.
Today, Poe's plans include the $4.99/month plan (10,000 points per day), the $19.99/mo plan (1 million points per month), the $49.99/mo plan (2.5 million points per month), the $99.99 plan (5 million points per month), and the 249.99/MO plan (12 million points per month).
Developers can also purchase additional points at a rate of $30,000,000 tokens. The add-on token is not in a fixed package, so customers can pay dollars to get the token based on that rate.
Through this API, developers can run tools such as cursors, klein, continuation, ROO and more, everything else that works with the OpenAI compatible chat completion API. Today, the platform offers access to over 100 models, ranging from audio, text, images and video generation.
These multimodal models include Imagen 4, GPT Image 1, Flux Kontext, Seedream 3.0, Veo 3, Runway Gen 4 Turbo, Kling 2.1, ElevenLabs, and Lyria.
Image credit: Quora
“We're now using a private bot built on a POE and making it possible for developers to use it through their API.
TechCrunch Events
San Francisco | October 27-29, 2025
The API provides a way for developers to use different models, while the POE also offers tools aimed at consumers. Earlier this year, the company introduced a new way to make it easier for users to create AI-powered apps. It also provides templates for building server bots, prompt bots, and image generation bots.
Currently, developers need to manually select and manage model usage. Jones said he would consider adding budget management capabilities in the future based on developer feedback.