Quick Start

Reduce AI API costs with two lines of configuration. Savings grow with conversation length. No code changes, no SDK, no vendor lock-in.

export OPENAI_BASE_URL=https://api.lexisaas.com/v1

lx_live_your_key_here:sk-your-provider-key

Authentication

LEXI uses a single composite API key that combines your LEXI key and provider key. This works with any OpenAI-compatible client — no custom headers needed.

Authorization: Bearer lx_live_your_key_here:sk-your-provider-key

Authorization: Bearer lx_live_your_key_here

Python (OpenAI)

Drop-in replacement using the official openai Python package. Set the base URL and use the composite key as your API key.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.lexisaas.com/v1",
    api_key="lx_live_your_key_here:sk-your-openai-key"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello, world!"}]
)
print(response.choices[0].message.content)

Requires openai >= 1.0. Install with pip install openai.

Node.js (OpenAI)

Works with the official openai npm package. Set baseURL and use the composite key as your API key.

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.lexisaas.com/v1',
  apiKey: 'lx_live_your_key_here:sk-your-openai-key'
});

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello, world!' }]
});
console.log(response.choices[0].message.content);

Requires openai >= 4.0. Install with npm install openai.

cURL

Test directly from your terminal. Pass the composite key in the Authorization header.

curl https://api.lexisaas.com/v1/chat/completions \
  -H "Authorization: Bearer lx_live_your_key_here:sk-your-openai-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o","messages":[{"role":"user","content":"Hello"}]}'

Anthropic

Use the official Anthropic Python SDK with a custom base URL. The composite key goes in the api_key parameter.

import anthropic

client = anthropic.Anthropic(
    base_url="https://api.lexisaas.com/v1",
    api_key="lx_live_your_key_here:sk-ant-your-anthropic-key",
)

message = client.messages.create(
    model="claude-sonnet-4-5-20250929",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello, world!"}]
)
print(message.content[0].text)

import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  baseURL: 'https://api.lexisaas.com/v1',
  apiKey: 'lx_live_your_key_here:sk-ant-your-anthropic-key',
});

const message = await client.messages.create({
  model: 'claude-sonnet-4-5-20250929',
  max_tokens: 1024,
  messages: [{ role: 'user', content: 'Hello, world!' }]
});
console.log(message.content[0].text);

Google Gemini, xAI Grok, DeepSeek, Meta

LEXI auto-detects the provider from the model name. Just use the model name you normally would. All providers use the same OpenAI-compatible endpoint.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.lexisaas.com/v1",
    api_key="lx_live_your_key_here:your-google-api-key"
)

response = client.chat.completions.create(
    model="gemini-2.5-pro",  # Auto-routes to Google
    messages=[{"role": "user", "content": "Hello!"}]
)

curl https://api.lexisaas.com/v1/chat/completions \
  -H "Authorization: Bearer lx_live_your_key_here:xai-your-grok-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"grok-3","messages":[{"role":"user","content":"Hello"}]}'

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.lexisaas.com/v1',
  apiKey: 'lx_live_your_key_here:your-deepseek-key'
});

const response = await client.chat.completions.create({
  model: 'deepseek-chat',  // Auto-routes to DeepSeek
  messages: [{ role: 'user', content: 'Hello!' }]
});

Response Headers

LEXI adds diagnostic headers to every response so you can monitor compression performance and debug issues.

Rate Limits

Rate limits are applied per API key. When exceeded, requests return 429 Too Many Requests with a Retry-After header.

Supported Models

LEXI works with any model available through the supported providers. Just use the model name you normally would — LEXI auto-routes to the right provider based on the model name.

Frequently Asked Questions

Common questions about how LEXI Cloud works, data handling, and compatibility.