Skip to main content
1

Create an account

Sign up and create your organization, it takes a minute. New organizations receive a $1 welcome credit, so you can make your first requests before adding credits. The welcome credit is a promotion that may change or be discontinued at any time.
2

Create an API key

Go to the API Keys page in the dashboard and select Create key. Keys start with sk-prl-infapi- and are shown only once, so store yours somewhere safe. Then export it as an environment variable in your terminal:
3

Install an SDK

Pearl Inference is OpenAI-compatible, so you can use the official OpenAI SDKs, or skip the SDK and call the REST API directly from any language.
4

Run your first request

Point the client at the Pearl base URL https://inference.pearlresearch.ai/v1 and send a chat completion to any supported model. Organizations on the EU inference region call their own base URL instead, shown on the Settings page:
Prefer no code? The playground runs the same models in your browser, and every request, playground or SDK, shows up in your dashboard’s Analytics tab.

Going further

The same client can stream tokens, call tools, return strict JSON, reason step by step, and read images. Try these variations:

Stream the response

Set stream=True to receive the response token by token as it’s generated instead of waiting for the full reply:
Learn more about streaming →

Call a reasoning model

GLM-5.3 (the model from your first request above) and the DeepSeek V4 models work through a problem before answering. The thinking arrives in a separate reasoning field on the message, and the final answer in content, when streaming, read both fields off each chunk’s delta:
Learn more about reasoning models →

Use tools (function calling)

Every model in the catalog supports tool definitions, so the model can ask your code to run a function and use its result:
Learn more about function calling →

Get structured JSON

Set response_format to JSON mode and describe the shape you want in the system prompt to get parseable JSON back:
Learn more about structured outputs →

Analyze an image

GLM-5.3 Flash accepts images. Add an image_url block to the user message to ask questions about a picture:
The image_url.url field follows the OpenAI schema, but the endpoint does not fetch remote URLs, encode your image as a data:image/<format>;base64,… data URI first. (A remote URL is silently unresolvable at the inference engine and returns an upstream validation error.)
Learn more about vision →

Next steps

Models

Compare the catalog and pick the right model for your workload.

Concepts

How organizations, API keys, credits, and billing fit together.

Playground

Prototype prompts against every model in the browser.