> ## Documentation Index
> Fetch the complete documentation index at: /docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Build on Pearl Inference Platform

> OpenAI-compatible inference supporting the latest open-weight models, get started in minutes

Pearl Inference runs production inference for a curated set of open-weight models on the Pearl network. You bring any OpenAI SDK (or plain HTTP), point it at our base URL, and pay per token from a prepaid balance, no GPU provisioning, no contracts, no switching costs.

## Get started in minutes

> [card] [Quickstart](/docs/quickstart.md)
>
> Create an API key and make your first request in a few minutes.

> [card] [Playground](https://platform.pearlresearch.ai/playground)
>
> Chat with every model in the browser before writing any code.

> [card] [Models](/docs/models.md)
>
> Pick the right model for coding, chat, vision, or reasoning.

> [card] [Inference & Management API](/docs/reference/inference.md)
>
> Endpoints, parameters, responses, and status codes for running models and reading your usage and costs.

> [!TIP]
>
> Not sure where to start? Pick a model with the [model selection guide](/docs/models.md), run the [quickstart](/docs/quickstart.md), and skim [Concepts](/docs/concepts.md) to understand keys, credits, and billing.

## What you can build

> [card] [Chat completions](/docs/inference.md)
>
> OpenAI-compatible /chat/completions with streaming on every model.

> [card] [Function calling](/docs/function-calling.md)
>
> Connect models to your tools and APIs, supported across the catalog.

> [card] [Structured outputs](/docs/json-mode.md)
>
> JSON mode for reliable, machine-readable responses.

> [card] [Reasoning models](/docs/reasoning.md)
>
> GLM-5.3 and the DeepSeek V4 models expose their chain of thought in a separate field.

> [card] [Vision](/docs/vision.md)
>
> Image to text with GLM-5.3 Flash.

> [card] [Long context](/docs/models.md)
>
> Up to 1M tokens of context with DeepSeek and GLM models.

## The platform today

The platform currently serves **chat-model inference** through a deliberately curated catalog of latest open weights models spanning reasoning, coding, general chat, and vision. Every model is served on the same OpenAI-compatible endpoint and billed per token against your organization's prepaid credits.

## Resources

> [card] [Dashboard](https://platform.pearlresearch.ai/dashboard)
>
> Credits, usage analytics, and your organization at a glance.

> [card] [API keys](https://platform.pearlresearch.ai/api-keys)
>
> Create and manage the keys your applications authenticate with.

> [card] [Billing](https://platform.pearlresearch.ai/billing)
>
> Top up credits, set up auto-recharge, and view payment history.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.