Nvidia

AISDK provides first-class support for Nvidia with fully typed model APIs. Model capabilities are enforced at compile time using Rust's type system. This prevents model capability mismatches and guarantees the selected model is valid for the task (e.g. tool calling).

Installation

Enable the Nvidia provider feature:

cargo add aisdk --features nvidia

This installs AISDK with the Nvidia provider enabled. Once you have enabled the Nvidia provider, you can use all aisdk features with it.

Create a Provider Instance

To create a provider instance, call Nvidia::model_name(), where model_name is the Nvidia model you want to use. Model names are exposed as snake-case methods.

use aisdk::providers::Nvidia;

let nvidia = Nvidia::black_forest_labs_flux_1_dev();

This initializes the provider with:

Model: "black-forest-labs/flux.1-dev"
API key from environment (if set with NVIDIA_API_KEY)
Nvidia's default base URL (https://integrate.api.nvidia.com/v1)

Basic Text Generation

Example using LanguageModelRequest for text generation.

use aisdk::{
    core::LanguageModelRequest,
    providers::Nvidia,
};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {

    let nvidia = Nvidia::black_forest_labs_flux_1_dev();

    let response = LanguageModelRequest::builder()
        .model(nvidia)
        .prompt("Write a short poem about Rust.")
        .build()
        .generate_text()
        .await?;

    println!("Response text: {:?}", response.text());
    Ok(())
}

Provider Settings

You can customize provider configuration using Nvidia::builder()

API Key

let nvidia = Nvidia::<BlackForestLabsFlux1Dev>::builder()
    .api_key("your-api-key")
    .build()?;

If not specified, AISDK uses the NVIDIA_API_KEY environment variable.

Base URL

Useful when routing through a proxy, gateway, or self-hosted compatible endpoint.

let nvidia = Nvidia::<BlackForestLabsFlux1Dev>::builder()
    .base_url("https://integrate.api.nvidia.com/v1")
    .build()?;

Path (Full URL Override)

Use .path(...) to override the full request URL instead of only the base URL.

let nvidia = Nvidia::<BlackForestLabsFlux1Dev>::builder()
    .path("https://full-url.example/v1/chat/completions")
    .build()?;

Provider Name

For logging, analytics, and observability.

let nvidia = Nvidia::<BlackForestLabsFlux1Dev>::builder()
    .provider_name("Nvidia")
    .build()?;

Full Custom Configuration Example

let nvidia = Nvidia::<BlackForestLabsFlux1Dev>::builder()
    .api_key("your-api-key")
    .base_url("https://integrate.api.nvidia.com/v1")
    .path("https://full-url.example/v1/chat/completions")
    .provider_name("Nvidia")
    .build()?;

Dynamic Model Selection

For runtime model selection (e.g., loading models from config files), use DynamicModel:

Using model_name() Method with Default Settings

use aisdk::providers::Nvidia;

// Specify model as a string at runtime
let nvidia = Nvidia::model_name("black-forest-labs/flux.1-dev");

Using Builder Pattern with Custom Settings

use aisdk::{
    core::DynamicModel,
    providers::Nvidia,
};

let nvidia = Nvidia::<DynamicModel>::builder()
	.model_name("black-forest-labs/flux.1-dev")
	.api_key("your-api-key")
	.base_url("https://integrate.api.nvidia.com/v1")
	.path("https://full-url.example/v1/chat/completions")
	.provider_name("Nvidia")
	.build()?;

Warning: When using DynamicModel, model capabilities are not validated at compile time. This means there's no guarantee the model supports requested features (e.g., tool calls, structured output). For compile-time safety, use the typed methods like Nvidia::black_forest_labs_flux_1_dev().

Next Steps

Take a deeper look at text generation features Generating Text / Streaming Text
Explore Structured Output for reliable agent data.
Learn how to create Custom Tools.
Learn more about Agents.

Nvidia

On this page