---
title: Anyscale
description: Use Anyscale's Ray-based distributed inference with Nexus.
---

Anyscale provides Ray-based distributed inference for open-source models. Uses an OpenAI-compatible API.

## Installation

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

## Quick Start

```go
provider := anyscale.New(os.Getenv("ANYSCALE_API_KEY"))

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

## Options

| Option | Description |
|--------|-------------|
| `anyscale.WithBaseURL(url)` | Override the API base URL (default: `https://api.endpoints.anyscale.com/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 |
|-------|---------|-----------|-------------|-------------|
| `meta-llama/Llama-3-8b-chat-hf` | 8,192 | 4,096 | $0.15/M | $0.15/M |
| `meta-llama/Llama-3-70b-chat-hf` | 8,192 | 4,096 | $1.00/M | $1.00/M |