Pruna endpoints

pruna hosts public endpoints for your models in collaboration with the inference providers in the industry. These endpoints are optimized for speed, efficiency, and cost with Pruna. This makes them the fastest and most efficient way to run your models in production.

Why use Pruna endpoints?

Pruna endpoints are faster, cheaper, and better than running your own model endpoints from scratch — thanks to our integrated optimizations and cloud infrastructure partnerships. They offer:

  • Faster: Models are hosted optimized for for speed using the latest optimization algorithms.

  • Cheaper: Model optimizations reduce hardware requirements and reduce costs.

  • Better: Good optimizations can be lossless and those are our specialty.

Tip

Check out our benchmark comparison page for a head-to-head look at latency and price compared to self-hosting and other public endpoints. See how much time and money you can save.

Where to find Pruna endpoints?

pruna hosts public endpoints for your models in collaboration with major inference providers in the industry, like Replicate, Prodia, Runpod, Segmind, DeepInfra, and Wiro.

Tip

You can also find an overview of all our endpoints on our website: pruna.ai.

Text-to-image generation

Quick reference one-sheet guides for immediate use:

Cheatsheet

Quick reference cheatsheet for image generation prompts.

./image_generation/quickstart.rst
Full Guide

Full guide for image generation prompts.

./image_generation/advanced.rst

Image Editing

Quick reference one-sheet guides for immediate use:

Cheatsheet

Quick reference cheatsheet for image editing prompts.

./image_editing/quickstart.rst
Full Guide

Full guide for image editing prompts.

./image_editing/advanced.rst

Video Generation

Quick reference one-sheet guides for immediate use:

Cheatsheet

Quick reference cheatsheet for video generation prompts.

./video_generation/quickstart.rst
Full Guide

Full guide for video generation prompts.

./video_generation/advanced.rst

General guides

General guides about overlapping topics:

Addressing biases

General guide for addressing biases in the endpoints.

./general/addressing_biases.rst
Prompt engineering tools

General guide for prompt engineering tools to improve your prompts.

pru_JpQlC1tdB2q2bCQp6XQER1tULmcASVrJ

./general/prompt_engineering_tools.rst
curl -X “POST” “https://api.pruna.ai/v1/predictions

-H ‘Content-Type: application/json’ -H ‘apikey: pru_JpQlC1tdB2q2bCQp6XQER1tULmcASVrJ’ -H ‘Try-Sync: true’ -d $’{

“input”: {

“aspect_ratio”: “16:9”, “prompt”: “A yellow car”

}, “model”: “p-image”

}’