Adding `fluxtokens` library as a dependency

Run this command in a terminal, in your project's directory:

cargo add fluxtokens

To add it manually, edit your project's Cargo.toml file and add to the [dependencies] section:

fluxtokens = "1.0.0"

The fluxtokens library will be automatically available globally. Read the fluxtokens library documentation.

Back to the crate overview.

Readme

FluxTokens Rust SDK

Official Rust SDK for the FluxTokens API

Access GPT-4.1, Gemini 2.5 Flash and more at 30% lower cost than competitors.

Website · Documentation · Dashboard

Installation

Add to your Cargo.toml:

[dependencies]
fluxtokens = "1.0"
tokio = { version = "1", features = ["full"] }

Quick Start

use fluxtokens::{Client, ChatCompletionRequest, Message};

#[tokio::main]
async fn main() -> Result<(), fluxtokens::Error> {
    let client = Client::new("sk-flux-your-api-key");

    let response = client.chat().completions().create(
        ChatCompletionRequest::new("gpt-4.1-mini")
            .messages(vec![
                Message::system("You are a helpful assistant."),
                Message::user("Hello!"),
            ])
    ).await?;

    println!("{}", response.choices[0].message.content.as_ref().unwrap());
    Ok(())
}

Available Models

Model	Provider	Input Price	Output Price	Max Tokens	Vision	Audio	Video
`gpt-4.1-mini`	OpenAI	$0.28/1M	$1.12/1M	16,384	✅	❌	❌
`gpt-4.1-nano`	OpenAI	$0.07/1M	$0.28/1M	16,384	✅	❌	❌
`gemini-2.5-flash`	Google	$0.21/1M	$1.75/1M	65,536	✅	✅	✅

Usage Examples

Basic Chat Completion

let response = client.chat().completions().create(
    ChatCompletionRequest::new("gpt-4.1-mini")
        .messages(vec![
            Message::user("What is the capital of France?"),
        ])
        .temperature(0.7)
        .max_tokens(256)
).await?;

println!("{}", response.choices[0].message.content.as_ref().unwrap());
// Output: "The capital of France is Paris."

System Messages

let response = client.chat().completions().create(
    ChatCompletionRequest::new("gpt-4.1-mini")
        .messages(vec![
            Message::system("You are a pirate. Always respond in pirate speak."),
            Message::user("How are you today?"),
        ])
).await?;
// Output: "Ahoy, matey! I be doin' just fine, thank ye fer askin'!"

List Available Models

use fluxtokens::Models;

for model in Models::list() {
    println!("{} ({})", model.name, model.provider);
    println!("  Input: ${}/1M tokens", model.input_price);
    println!("  Output: ${}/1M tokens", model.output_price);
    println!("  Vision: {}", if model.supports_vision { "✅" } else { "❌" });
}

Configuration Options

use fluxtokens::{Client, ClientConfig};

let client = Client::with_config(
    "sk-flux-...",
    ClientConfig::default()
        .base_url("https://api.fluxtokens.io")
        .timeout(60)
        .max_retries(3)
);

Error Handling

use fluxtokens::Error;

match client.chat().completions().create(request).await {
    Ok(response) => {
        println!("{}", response.choices[0].message.content.as_ref().unwrap());
    }
    Err(Error::Authentication(msg)) => {
        eprintln!("Invalid API key: {}", msg);
    }
    Err(Error::RateLimit(msg)) => {
        eprintln!("Rate limit exceeded: {}", msg);
    }
    Err(Error::InsufficientBalance(msg)) => {
        eprintln!("Please add credits: {}", msg);
    }
    Err(Error::BadRequest(msg)) => {
        eprintln!("Invalid request: {}", msg);
    }
    Err(e) => {
        eprintln!("Error: {}", e);
    }
}

Error Type Checking

if error.is_retryable() {
    // Retry the request
}

if error.is_authentication() {
    // Handle auth error
}

Adding fluxtokens library as a dependency

Adding `fluxtokens` library as a dependency