Production — v2.0

Codex API
Infrastructure at Scale

High-performance OpenAI-compatible gateway for Codex models. Deploy in minutes, scale on demand, pay only for what you use.

POST https://api.redbtco.com/v1/chat/completions
99.9%
Uptime SLA
<50ms
Avg Latency
OpenAI
Compatible
Codex
Native Support
Features

Built for production

Everything you need to run Codex models in production — no DevOps required.

OpenAI-Compatible API

Drop-in replacement for /v1/chat/completions, /v1/responses, /v1/images — works with any OpenAI SDK.

🔄

Anthropic Messages

Native /v1/messages endpoint for Anthropic-compatible clients. One gateway, all protocols.

🖼️

Image Generation

Full DALL·E-compatible image generation and manipulation via /v1/images endpoints.

📊

Usage Analytics

Real-time dashboards, per-API-key tracking, cost breakdowns, and exportable reports.

🛡️

Smart Rate Limiting

Per-account concurrency, global RPM, cooldown recovery, health scoring — automatic.

🌍

Global Edge

Deployed on low-latency infrastructure. Access via Cloudflare for worldwide reach.

API Reference

Ready in 3 lines

Use any OpenAI SDK — just change the base URL.

# Python — OpenAI SDK
import openai
client = openai.OpenAI(
    base_url="https://api.redbtco.com/v1",
    api_key="your-api-key"
)
response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "Hello!"}]
)
Chat Completions
POST /v1/chat/completions
OpenAI-compatible chat endpoint
Responses
POST /v1/responses
Native Codex responses forwarding
Models
GET /v1/models
List available models
Pricing

Pay-as-you-go

Transparent pricing with volume discounts. No monthly minimums.

Starter
Free
up to 1K requests/day
  • 1,000 requests / day
  • 2 concurrent requests
  • Community support
  • All models
Get Started
Enterprise
Custom
volume pricing
  • Dedicated capacity
  • SLA guarantee
  • 24/7 support
  • Custom contracts
  • On-premise option
Contact Us
FAQ

Common questions

What models are available?

We proxy the full Codex model catalog — GPT-5.x series across all tiers (Flex, Plus, Pro, Max). Use GET /v1/models to see the current list.

Is it OpenAI-compatible?

Yes. Our gateway is fully compatible with the OpenAI SDK, Anthropic SDK, and any HTTP client. Just change the base URL.

How is billing calculated?

Usage is tracked per API key with a 5-hour rolling window. View detailed usage in your client dashboard.

What's your uptime guarantee?

We maintain 99.9% uptime with automatic failover across multiple Codex accounts. Status updates at status.redbtco.com.