---
source_url: "https://inference-docs.cerebras.ai/integrations/parallel"
title: Get Started with Parallel - Cerebras Inference
mirrored_at: 2026-08-12T03:04:52.715Z
host: inference-docs.cerebras.ai
cited_in_42a: true
mirror_canonical: "https://index.42a.ai/inference-docs.cerebras.ai/integrations/parallel"
---

> **Original source:** https://inference-docs.cerebras.ai/integrations/parallel

Learn how to build AI agents with web search, extraction, and monitoring capabilities using Parallel APIs and Cerebras models.

Parallel provides a suite of web research APIs built specifically for AI agents. By combining Parallel’s high-accuracy Search, Extract, and Monitor APIs with Cerebras’ ultra-fast inference, you can build agents that search the web, extract structured content, and monitor for real-time updates—all with sub-second response times.

## Prerequisites

Before you begin, ensure you have:

-   **Cerebras API Key** - Get a free API key [here](https://cloud.cerebras.ai/?utm_source=cerebras&utm_campaign=parallel).
-   **Parallel API Key** - Visit [Parallel](https://parallel.ai/?utm_source=cerebras&utm_campaign=parallel) and create an account to get your API key.
-   **Python 3.10 or higher** or **Node.js 22 or higher**

## Configure Parallel with Cerebras

1

2

3

## Core APIs

Parallel offers three main APIs that work together for comprehensive web research:

API

Purpose

Best For

**Search**

High-accuracy web search with compressed excerpts

Finding relevant information across the web

**Extract**

Convert web pages and PDFs to LLM-ready markdown

Deep content extraction from specific URLs

**Monitor**

Watch the web for state changes

Real-time alerts and continuous intelligence

## Search API

The Search API is engineered for AI agents, delivering the most relevant, token-efficient web data at the lowest cost.

### Basic Search

### Search with Cerebras Synthesis

Combine Parallel’s search with Cerebras’ fast inference to create a complete research workflow:

## Extract API

The Extract API converts web pages and PDFs to LLM-ready markdown. It supports two modes:

-   **Compressed excerpts**: Dense, objective-focused extractions
-   **Full content extraction**: Complete page content in markdown format

### Extract Compressed Excerpts

### Extract Full Content

### Search + Extract Workflow

Combine Search and Extract for comprehensive research:

## Monitor API

The Monitor API flips the traditional pull model to push—create queries that trigger notifications when new information is published to the web.

### Create a Monitor

### Monitor Use Cases

-   **Proactive sub-agent**: Create agents that are invoked when web changes are detected
-   **Workflow trigger**: Trigger workflows when new information surfaces (e.g., add leads to CRM)
-   **Continuous intelligence feed**: Maintain always-up-to-date data feeds for investment research

## Building a Search Agent with Vercel AI SDK

For production applications, you can build a full-stack search agent using the Vercel AI SDK with Cerebras:

skip

## Choosing the Right Cerebras Model

Different research tasks benefit from different models:

Model

Best For

Speed

`gpt-oss-120b`

Complex multi-step research, nuanced synthesis

Fast

`zai-glm-4.7`

Tool-heavy agents, coding documentation research

Fast

## Next Steps

-   Explore [Parallel’s full documentation](https://docs.parallel.ai/?utm_source=cerebras&utm_campaign=parallel) for advanced features
-   Try different [Cerebras models](https://inference-docs.cerebras.ai/models) to optimize for your research use case
-   Check out the [Parallel + Cerebras Search Agent Cookbook](https://parallel.ai/blog/cookbook-search-agent?utm_source=cerebras&utm_campaign=parallel) for a complete implementation example
-   Build with the [Vercel AI SDK](https://inference-docs.cerebras.ai/integrations/vercel-ai-sdk) for production-ready streaming agents

## Troubleshooting

Search results aren't relevant enough

Try these approaches:

1.  **Be more specific in your objective** - Instead of “AI news”, try “Recent announcements about large language model capabilities from major AI labs”
2.  **Use multiple search queries** - Provide explicit `search_queries` to cover different angles
3.  **Increase max\_results** - Get more results and let the LLM filter for relevance
4.  **Use the “pro” processor** - For fresher, higher-quality results (at higher cost)

Extraction is missing content

Some pages require special handling:

1.  **JavaScript-rendered content** - Parallel handles most JS-rendered sites, but some may require additional wait time
2.  **PDFs** - Parallel supports multi-page PDF extraction, including images
3.  **Paywalled content** - Some content may not be accessible; check the extraction status in the response

Which Cerebras model should I use for research tasks?

Choose based on your research complexity:

-   **Text synthesis and structured extraction**: `gpt-oss-120b`
-   **Pages or artifacts that include image input**: preview `gemma-4-31b`
-   Check the [model catalog](https://inference-docs.cerebras.ai/models/overview) before selecting other preview models

## Additional Resources

-   [Parallel Search API Documentation](https://parallel.ai/blog/parallel-search-api)
-   [Parallel Extract API Documentation](https://docs.parallel.ai/extract/extract-quickstart)
-   [Parallel Monitor API Documentation](https://docs.parallel.ai/monitor-api/monitor-quickstart)
-   [Cerebras Models Overview](https://inference-docs.cerebras.ai/models)