14 models, native protocol passthrough, billed per token. From 90% OFF of list price.
as of 2026-10-27
OpenAI has two generations of text models and one image line on RouteMux. The text models answer on OpenAI Chat Completions and OpenAI Responses, and also over Anthropic Messages, so an Anthropic-shaped client can call them without rewriting its request layer; the image models use the OpenAI Images endpoints, /v1/images/generations and /v1/images/edits.
The GPT-6 family arrived in September 2026 in three tiers: Astra (September 3) for the hardest end-to-end work, Sol in the middle, and Luna (September 22) as the smallest and cheapest. GPT-6.1 Sol, released September 29, upgrades Sol, and OpenAI says it comes close to Astra on complex coding and professional work. Across GPT-6, reasoning cannot be set to none — only GPT-6 Sol still accepts it.
The GPT-5.6 family (July 9, 2026) — Sol, Terra and Luna — remains callable, accepts reasoning effort none, and is a sensible pin for prompts tuned against it. Mind the naming: GPT-5.6 Sol is the top of 5.6, while GPT-6 Sol is the middle of 6. For images, GPT Image 2.5 comes as Flare and Sunburst: Flare is faster and the default for most apps; OpenAI recommends Sunburst where editing precision matters most, at the cost of longer generation times.
Prepaid wallet billed on actual usage. No monthly fee, no minimum, credits never expire. The protocol layer is a native passthrough, not a translation shim: request bodies and SSE streaming match the official API, so clients only need a new base URL.
Every model is priced against the provider's published per-million-token rate at a fixed discount. Cache reads and writes use the same ratio, with no surcharge. The exact per-model rate is in the table above and always reflects current pricing.
Passed through. Request bodies, SSE streaming format, cache control and extended-thinking parameters match the upstream provider. Point your existing SDK at our base URL and the rest of your code stays unchanged.
No. The prepaid wallet is charged by actual token usage, with no monthly fee and no minimum spend. Unused balance can be refunded under our Terms of Service.