Vision · language

Use Llama 3.2 90B Vision with Rust

Updated 2026-05-21 · By XALEN

How to use Llama 3.2 90B Vision (Vision, 90B) with Rust. Install, authenticate, and make your first API call in minutes. Working code example included.

Model
Llama 3.2 90B Vision
90B · 128K context · $0.06 input
Framework
Rust
language · cargo add async-openai

1. Install

cargo add async-openai

2. Code

use async_openai::{Client, config::OpenAIConfig, types::*};

#[tokio::main]
async fn main() {
    let config = OpenAIConfig::new()
        .with_api_key("xln_test_YOUR_KEY")
        .with_api_base("https://api.xalen.io/v1");
    let client = Client::with_config(config);

    let request = CreateChatCompletionRequestArgs::default()
        .model("llama-3-2-90b-vision")
        .messages(vec![ChatCompletionRequestUserMessageArgs::default()
            .content("Hello from Rust!").build().unwrap().into()])
        .build().unwrap();

    let response = client.chat().create(request).await.unwrap();
    println!("{}", response.choices[0].message.content.as_ref().unwrap());
}

Llama 3.2 90B Vision with Other Frameworks

Python JavaScript React Next.js Flask FastAPI Django Express.js

Other Models with Rust

Vedika Standard Vedika Fast Vedika Pro Ultra Vedika Vision Vedika Code Vedika Astro Agent

200+ models. One API. Works with any framework.

Get API Key

Last updated: 2026-05-21