Oct 25, 2026

GPT-6.1 Sol is on the gateway (`gpt-6.1-sol`), plus a `fast` service tier for OpenAI models

OpenAI released GPT-6.1 Sol at DevDay on 2026-09-29: near-Astra results on coding, computer use and document work at one-fifth of Astra's upstream price. It is live here as `gpt-6.1-sol` — 75 AP in / 300 AP out per 1K tokens, 128K max output, reads images, reasoning on (reasoning_effort low/medium/high/xhigh; default low). Two upstream limits you should know: function tools are not accepted for the gpt-6 family on `/v1/chat/completions` (we return tools_unsupported_for_model instead of forwarding a doomed call; use gpt-5.6-sol / gpt-5.6-terra for tool calling), and temperature must stay at its default. New on every OpenAI-hosted model: "service_tier": "fast" asks OpenAI for its Fast tier at 2× the AP rate; the response header X-AICU-Service-Tier tells you what you actually got, and if OpenAI falls back to standard you pay the standard rate. ultrafast is a Responses API tier upstream and is not available through Chat Completions yet.