FireworksAi

AISDK provides first-class support for FireworksAi 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 FireworksAi provider feature:

cargo add aisdk --features fireworks-ai

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

Create a Provider Instance

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

use aisdk::providers::FireworksAi;

let fireworks-ai = FireworksAi::models_deepseek_r1_0528();

This initializes the provider with:

Model: "accounts/fireworks/models/deepseek-r1-0528"
API key from environment (if set with FIREWORKS_API_KEY)
FireworksAi's default base URL (https://api.fireworks.ai/inference/v1/)

Basic Text Generation

Example using LanguageModelRequest for text generation.

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

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

    let fireworks-ai = FireworksAi::models_deepseek_r1_0528();

    let response = LanguageModelRequest::builder()
        .model(fireworks-ai)
        .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 FireworksAi::builder()

API Key

let fireworks-ai = FireworksAi::<ModelsDeepseekR10528>::builder()
    .api_key("your-api-key")
    .build()?;

If not specified, AISDK uses the FIREWORKS_API_KEY environment variable.

Base URL

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

let fireworks-ai = FireworksAi::<ModelsDeepseekR10528>::builder()
    .base_url("https://api.fireworks.ai/inference/v1/")
    .build()?;

Path (Full URL Override)

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

let fireworks-ai = FireworksAi::<ModelsDeepseekR10528>::builder()
    .path("https://full-url.example/v1/chat/completions")
    .build()?;

Provider Name

For logging, analytics, and observability.

let fireworks-ai = FireworksAi::<ModelsDeepseekR10528>::builder()
    .provider_name("FireworksAi")
    .build()?;

Full Custom Configuration Example

let fireworks-ai = FireworksAi::<ModelsDeepseekR10528>::builder()
    .api_key("your-api-key")
    .base_url("https://api.fireworks.ai/inference/v1/")
    .path("https://full-url.example/v1/chat/completions")
    .provider_name("FireworksAi")
    .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::FireworksAi;

// Specify model as a string at runtime
let fireworks-ai = FireworksAi::model_name("accounts/fireworks/models/deepseek-r1-0528");

Using Builder Pattern with Custom Settings

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

let fireworks-ai = FireworksAi::<DynamicModel>::builder()
	.model_name("accounts/fireworks/models/deepseek-r1-0528")
	.api_key("your-api-key")
	.base_url("https://api.fireworks.ai/inference/v1/")
	.path("https://full-url.example/v1/chat/completions")
	.provider_name("FireworksAi")
	.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 FireworksAi::models_deepseek_r1_0528().

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.

FireworksAi

On this page