Blog

Guides, comparisons, and engineering notes from the team building AnyRouter — one OpenAI-compatible endpoint in front of every model.

Model releases

Changelog

Models added or disabled, and platform upstreams we turned off.

All releases

Step 5 Preview

2026-09-29

StepFun's next-generation flagship base model joins the catalog BYOK-only on AIHubMix — 1M-token context, 64K max output, text/image/video input, and adjustable reasoning at $1.08 / $3.0888 per million input / output tokens.

Step 5 Preview

Claude Sonnet 5.5

2026-09-29

Anthropic's Claude Sonnet 5.5 joins the catalog — the direct upgrade to Claude Sonnet 5, at the same $2 / $10 per million input / output tokens, with adaptive thinking on by default, 1M-token context, 128K max output, and vision input.

Claude Sonnet 5.5

BGE-M3, BGE Multilingual Gemma 2, Mistral Small 3.2 — now on OVHcloud AI Endpoints

2026-09-27

Two BAAI multilingual embedding models and Mistral's current 24B instruction model join the catalog, both on a new BYOK provider: OVHcloud AI Endpoints.

BGE-M3BGE Multilingual Gemma 2Mistral Small 3.2 24B Instruct

Guides

How to route every model through one OpenAI-compatible endpoint — setup, coding agents, MCP, free models, and BYOK.

All 20

Comparisons

How AnyRouter stacks up against calling providers directly or through another gateway — pricing, markup, and lock-in.

All 5

Product

New features, launches, and changes to the gateway — credits, the shared key pool, on-device models, and the dashboard.

All 16

Data

What the traffic actually shows — most-used models, real latency, and the economics of running a router.

All 2

Engineering

How the gateway is built on Cloudflare Workers — routing, failover, streaming, and the edge trade-offs behind it.

All 2