Official Libraries & Developer Tools

Developer SDKs

Integrate Flixil into your preferred stack in minutes. Native client libraries with full streaming, automatic retries, and rate limit resilience.

Python SDK

Official

Full async client for OpenAI, Anthropic, Gemini, and Groq with automatic token metering, retries, and semantic caching.

Targetflixil (PyPI)

from flixil import FlixilClient

client = FlixilClient(api_key="flix_live_sec_...")

# Drop-in completions with automatic token & cost telemetry
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Generate unit tests."}],
    temperature=0.2
)
print(response.choices[0].message.content)

Open-source on GitHubView Repository

TypeScript / Node.js SDK

Official

Type-safe TypeScript SDK compatible with Next.js, Bun, Node.js, Cloudflare Workers, and Deno edge runtimes.

Target@flixil/sdk (npm)

import { Flixil } from "@flixil/sdk";

const flixil = new Flixil({
  apiKey: process.env.FLIXIL_API_KEY,
});

const completion = await flixil.chat.completions.create({
  model: "claude-3-5-sonnet",
  messages: [{ role: "user", content: "Analyze system metrics." }],
});

console.log(completion.choices[0].message.content);

Open-source on GitHubView Repository

Go SDK

Official

High-concurrency Go client designed for high-throughput microservices and streaming token telemetry pipelines.

Targetgithub.com/flixil-ai/flixil-go

package main

import (
    "context"
    "fmt"
    "github.com/flixil-ai/flixil-go"
)

func main() {
    client := flixil.NewClient("flix_live_sec_...")
    resp, err := client.Chat.Create(context.Background(), &flixil.ChatRequest{
        Model: "deepseek-reasoner",
        Messages: []flixil.Message{{Role: "user", Content: "Optimize SQL."}},
    })
    if err != nil { panic(err) }
    fmt.Println(resp.Choices[0].Message.Content)
}

Open-source on GitHubView Repository

Edge & Fetch Client

Universal

Lightweight zero-dependency client compatible with Cloudflare Workers, Vercel Edge, Deno, and standard Web Fetch.

TargetNative Standard Fetch

const response = await fetch("https://api.flixil.com/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer flix_live_sec_...",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "gpt-4o",
    messages: [{ role: "user", content: "Optimize query plan." }],
  }),
});
const data = await response.json();
console.log(data.choices[0].message.content);

Open-source on GitHubView Repository