# Parasail: Cloud GPU Platform for AI Inference

Parasail is a cloud GPU platform for AI inference. We aggregate top AI hardware providers to give you scalable, on-demand access to powerful computing resources—without costly hardware investments or lengthy contracts.

We offer three ways to run inference, each designed for a different workload pattern:

## Serverless

On-demand, pay-per-token inference for popular open-source models. No setup required—just call the API.

## Dedicated Instances

Private GPU endpoints with full control over model, hardware, and scaling. Ideal for production workloads.

## Batch Processing

Process millions of inferences at 50% off serverless pricing. OpenAI-compatible batch API.

## Pick a product based on your workload:

| If you...  | Use  | Why  |
| ----------- | ----  | ----  |
| Want to call a popular open-source model with no setup | [Serverless](https://docs.parasail.io/parasail-docs/products/overview) | Pay-per-token, instant, OpenAI-compatible |
| Need a specific or private model, predictable latency, or production SLAs | [Dedicated Instances](https://docs.parasail.io/parasail-docs/products/overview-1) | Private GPU endpoint with full control over model, hardware, and scaling |
| Process large volumes offline where real-time isn't required | [Batch](https://docs.parasail.io/parasail-docs/products/quickstart) | 50% off serverless pricing, up to millions of requests |

## Find your path

Choose the option that best matches what you're trying to do:

- **Chat and text generation**: Build chatbots, assistants, and text generation pipelines  
- **RAG and embeddings**: Build retrieval-augmented generation and vector search systems  
- **Batch at scale**: Process large volumes of prompts, images, or text offline  
- **Agents and tool calling**: Build agentic workflows with function calling and multi-step reasoning

## Quickstart

Make your first API call in under two minutes:

- **Serverless quickstart**: Call a serverless model with the OpenAI SDK  
- **Dedicated quickstart**: Deploy your own model on a dedicated GPU  
- **Batch quickstart**: Submit a batch job in five lines of Python

## API reference

Parasail's API is fully OpenAI-compatible. Point your existing OpenAI SDK at our base URL and start making requests.

- **Base URL**: `https://api.parasail.io/v1`  
- **Auth**: `Authorization: Bearer <PARASAIL_API_KEY>`  
- **Get an API key**: [https://www.saas.parasail.io/keys](https://www.saas.parasail.io/keys)

See the [API Reference](https://docs.parasail.io/parasail-docs/api-reference/authentication) for full details on authentication, endpoints, and parameters.

## For AI coding agents

Building on Parasail on behalf of a user? Read [`llms.txt`](https://github.com/parasail-ai/gitbook-doc/tree/main/llms.txt) for a flat index of every page, then see [For AI Coding Agents](https://github.com/parasail-ai/gitbook-doc/tree/main/resources/for-ai-coding-agents.md) for per-product setup notes. In short: use the OpenAI SDK against `https://api.parasail.io/v1` with the `PARASAIL_API_KEY` environment variable—every endpoint is OpenAI-compatible.

## Explore

- **Guides**: Step-by-step tutorials for common tasks
- **Billing**: Pricing and billing details
- **Operations**: Production readiness, retries, limits, and quotas
- **Security**: Security, privacy, Trust Center, and account controls