GPT-6.1 Terra and Claude 5.5 are on the gateway
Six new models on one cflx_ key: GPT-6.1 Terra, GPT-6.1 Sol and GPT-6 Luna from OpenAI, and Claude Opus 5.5, Sonnet 5.5 and Haiku 5.5 from Anthropic. What each is for, and what it costs through us.
Oct 27, 2026
Every model, one key: the new lineup
The gateway now spans the full GPT-5.x/6 line and the Claude 5 family — plus embeddings. Nothing changes in your code to add them.
Sep 10, 2026
GPT-6 Astra, and how we use it
OpenAI's new flagship is live on the withConflux gateway. What it's good at, what it costs through us, and exactly where we route it.
Sep 10, 2026
What is an AI gateway? (and when you need one)
A single endpoint in front of every AI provider — one key, one bill, with routing, caching and spend caps. Here's how it works and when it's worth it.
Oct 1, 2026
Cut your AI bill with model routing
Most teams overpay by sending every request to their most expensive model. Routing by task is the cheapest optimization you'll ever ship.
Oct 1, 2026
How to compare two AI models (and what actually matters)
Price per token is only the start. Here is how to compare two models on a month of real work, how fast they answer, and how hard it is to switch.
Nov 7, 2026
API speed, measured on our gateway: typical, slow and first token
How fast a model answers is not one number. Here is how we measure it from live calls, and why we show a range instead of a rank.
Nov 7, 2026