Xyris Logo Xyris Console

Powerful AI Models, Built for Developers

Access state-of-the-art language models via a clean, OpenAI-compatible API. Build faster with competitive pricing, high throughput, and zero infrastructure overhead.

Start Free →

$500 Free Credit • No Credit Card Required

Every new account is credited with $500.00 in free API usage instantly. Start building immediately, with no billing setup or waiting.

Available Models

Production-ready models you can call today. Drop in your API key and start generating.

Ultra-Low Latency

Responses start streaming in milliseconds. Our infrastructure is optimized for first-token speed so your users never wait.

Industry-Best Pricing

At $0.50 input / $0.80 output per 1M tokens, Xyris models cost a fraction of legacy providers, without sacrificing quality.

OpenAI-Compatible API

One-line migration. Change your baseURL and apiKey, and everything else stays the same. Works with any OpenAI SDK.

Secure & Private

Your requests are never logged for training. Per-key access control, usage tracking, and instant revocation built in.

Real-Time Usage Analytics

Monitor token consumption, latency, and spend in real time from your developer console, with no third-party dashboards needed.

Global Edge Delivery

Requests are routed to the nearest inference node automatically. Consistent performance regardless of where your users are located.

Lightning Fast Integration

Swap a single line of code in your existing applications to start routing completions through Xyris at a fraction of the cost.

OpenAI SDK Compatible
import openai

client = openai.OpenAI(
    base_url="https://xyris-api-proxy.vercel.app/v1",
    api_key="your-xyris-token-here"
)

response = client.chat.completions.create(
    model="XYRIS-FLASH",
    messages=[{"role": "user", "content": "Hello, Xyris!"}],
    stream=True
)

for chunk in response:
    print(chunk.choices[0].delta.content or "", end="")

Unbeatable Price Performance

We host optimized inference instances directly at the edge, offering the same intelligence at up to 70% cheaper rates than raw legacy APIs.

Xyris Flash

$0.50 / 1M Input Tokens
  • $0.80 / 1M Output Tokens
  • ~10ms Time-To-First-Token
  • 128K Context Window
Deploy for Free
Best Reasoning Value

GPT-5.5

$0.70 / 1M Input Tokens
  • $1.20 / 1M Output Tokens
  • Highly Capable Code Reasoner
  • 200K Extended Context
Get Started Now

Console Settings

Manage your developer credentials, API tokens, and access key sessions.

User Profile Session

Name Loading...
Email Address Loading...
Role Clearance Loading...
Joined Date Loading...

API Key Generator

Generate unique access keys to authenticate completions client apps.

SAVE KEY DETAILS (IT WILL NOT BE SHOWN AGAIN): xy-token-value

Active API Keys

Revoking a key immediately breaks active completion instances.

Key Name API Key Created Date Actions

Inference Playground

Test models and prompt behaviors in real-time. Playground actions consume your credit balance.

Available Credit: $0.00
Select a model and send a message to start testing completions.

Usage Statistics

Monitor your completion requests, latency, and credits consumed.

TOTAL REQUESTS
0
CREDITS CONSUMED
$0.00
AVG REQUEST LATENCY
0ms

Recent Request Logs

Your past 50 gateway request transactions.

Timestamp Method Path Model Used Approx Cost Latency Status

Redeem Gift Code

Enter a promotional or voucher code to add credits to your balance.