---
title: Deepinfra
description: Use Deepinfra for serverless open-source model inference with Nexus.
---

Deepinfra provides serverless inference for open-source models with embedding support. Uses an OpenAI-compatible API.

## Installation

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

## Quick Start

```go
provider := deepinfra.New(os.Getenv("DEEPINFRA_API_KEY"))

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

## Options

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

## Capabilities

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

## Models

| Model | Context | Max Output | Input Price | Output Price |
|-------|---------|-----------|-------------|-------------|
| `meta-llama/Meta-Llama-3.1-405B-Instruct` | 131K | 4,096 | $1.79/M | $1.79/M |
| `meta-llama/Meta-Llama-3.1-8B-Instruct` | 131K | 4,096 | $0.06/M | $0.06/M |
| `BAAI/bge-large-en-v1.5` | 512 | — | $0.01/M | — |