Integrate Edgee to your stack

Learn how to integrate Edgee to your stack and start using Edgee services in your application.

Edgee can be integrated to your stack in different ways. You can use our SDKs, use our API directly, or use our official integrations with other tools.

Use our SDKs

TypeScript

npm install edgee

Python

pip install edgee

Go

go get github.com/edgee-ai/go-sdk

Rust

cargo install edgee

Then, you can start using Edgee in your application. Here is a quick example:

TypeScript

import Edgee from 'edgee';

const edgee = new Edgee(process.env.EDGEE_API_KEY);

const response = await edgee.send({
  model: 'gpt-5.2',
  input: 'What is the capital of France?',
});

console.log(response.content);
// "The capital of France is Paris."

if (response.compression) {
  console.log(`Tokens saved: ${response.compression.saved_tokens}`);
  console.log(`Reduction: ${response.compression.reduction}%`);
  console.log(`Cost savings: ${(response.compression.cost_savings / 1_000_000).toFixed(4)}`);
  console.log(`Compression time: ${response.compression.time_ms}ms`);
}
// "Tokens saved: 100"
// "Reduction: 50%"
// "Cost savings: $0.0093"
// "Compression time: 100ms"

Python

from edgee import Edgee

edgee = Edgee(api_key=os.environ["EDGEE_API_KEY"])

response = edgee.send(
    model="gpt-5.2",
    input="What is the capital of France?"
)

print(response.content)
# "The capital of France is Paris."

if response.compression:
    print(f"Tokens saved: {response.compression.saved_tokens}")
    print(f"Reduction: {response.compression.reduction}%")
    print(f"Cost savings: ${response.compression.cost_savings / 1_000_000:.4f}")
    print(f"Compression time: {response.compression.time_ms}ms")
# "Tokens saved: 100"
# "Reduction: 50%"
# "Cost savings: $0.0093"
# "Compression time: 12ms"

Go

package main

import (
    "fmt"
    "os"
    "github.com/edgee-ai/go-sdk"
)

func main() {
    client := edgee.NewClient(os.Getenv("EDGEE_API_KEY"))

    response, _ := client.Send(edgee.SendParams{
        Model: "gpt-5.2",
        Input: "What is the capital of France?",
    })

    fmt.Println(response.Content)
    // "The capital of France is Paris."

    if response.Compression != nil {
        fmt.Printf("Tokens saved: %d\n", response.Compression.SavedTokens)
        fmt.Printf("Reduction: %f%%\n", response.Compression.Reduction)
        fmt.Printf("Cost savings: $%.4f\n", float64(response.Compression.CostSavings)/1_000_000)
        fmt.Printf("Compression time: %dms\n", response.Compression.TimeMs)
    }
    // "Tokens saved: 100"
    // "Reduction: 50%"
    // "Cost savings: $0.0093"
    // "Compression time: 12ms"
}

Rust

use edgee::Edgee;

let api_key = std::env::var("EDGEE_API_KEY").expect("EDGEE_API_KEY not set");
let edgee = Edgee::new(api_key);

let response = edgee.send(edgee::SendRequest {
    model: "gpt-5.2".to_string(),
    input: "What is the capital of France?".to_string(),
});

println!("{}", response.output_text);
// "The capital of France is Paris."

if response.compression {
    println!("Tokens saved: {}", response.compression.saved_tokens);
    println!("Reduction: {}", response.compression.reduction);
    println!("Cost savings: ${}", response.compression.cost_savings / 1_000_000);
    println!("Compression time: {}ms", response.compression.time_ms);
}
// "Tokens saved: 100"
// "Reduction: 50%"
// "Cost savings: $0.0093"
// "Compression time: 12ms"

To learn more about the SDKs, see the individual SDK pages.

Use Edgee in your Coding Assistant

The easiest way is to use the Edgee CLI — it handles authentication and configuration automatically:

curl -fsSL https://install.edgee.ai | bash
edgee init
edgee launch claude

You can also configure your coding assistant manually:

Edgee CLI

The fastest path: install, authenticate, and launch in two commands. Supports Claude Code and Codex.

Claude Code

Manual configuration for Claude Code via environment variables or settings file.

Codex

Launch Codex through Edgee using the CLI.

OpenCode

Connect OpenCode’s CLI agent to Edgee for cost savings and unified access to multiple models.

Use Edgee in your Framework

You can use Edgee in your preferred Framework by using our official integrations.

OpenAI SDK

Point your existing OpenAI SDK at Edgee — no code changes, just swap the base URL and API key.

Anthropic SDK

Use the Anthropic SDK with Edgee to access Claude and other models through one gateway.

LangChain

Run chains, agents, and RAG pipelines through Edgee for cost tracking and compression.