---
title: Cerebras
description: Use Cerebras Wafer Scale Engine for ultra-fast Llama inference with Nexus.
---

Cerebras provides ultra-fast inference on their Wafer Scale Engine hardware. Uses an OpenAI-compatible API.

## Installation

```go
import "github.com/xraph/nexus/providers/cerebras"
```

## Quick Start

```go
provider := cerebras.New(os.Getenv("CEREBRAS_API_KEY"))

gw := nexus.New(
    nexus.WithProvider(provider),
)
```

## Options

| Option | Description |
|--------|-------------|
| `cerebras.WithBaseURL(url)` | Override the API base URL (default: `https://api.cerebras.ai/v1`) |

## Capabilities

| Capability | Supported |
|-----------|-----------|
| Chat | Yes |
| Streaming | Yes |
| Embeddings | No |
| Vision | No |
| Tools | No |
| Thinking | No |

## Models

| Model | Context | Max Output | Input Price | Output Price |
|-------|---------|-----------|-------------|-------------|
| `llama3.1-8b` | 8,192 | 4,096 | $0.10/M | $0.10/M |
| `llama3.1-70b` | 8,192 | 4,096 | $0.60/M | $0.60/M |