Checked fact 115511 Oct 2026Models and releases

The changelog says to use gpt-6.1-sol with service_tier: "ultrafast" to reduce the time between generated output tokens.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

Use `gpt-6.1-sol` with `service_tier: "ultrafast"` to reduce the time between generated output tokens.

What the source said when we opened it, on 11 Oct 2026.

The source

OpenAI API changelog
OpenAI · 2026-10-08

Open the source archived copy

Checked

Checked by the notis newsroom on 11 Oct 2026, against the source above.

In the story

OpenAI added Ultrafast mode for GPT-6.1 Sol, priced at $12 per million input tokens. 11 Oct 2026

Cite this fact

Short permanent address

In a sentence

“The changelog says to use gpt-6.1-sol with service_tier: "ultrafast" to reduce the time between generated output tokens.” ai notis, checked 11 Oct 2026. Source: OpenAI API changelog (OpenAI). https://ainotis.com/c/1155

As a reference (APA style)

ai notis. (2026, October 11). The changelog says to use gpt-6.1-sol with service_tier: "ultrafast" to reduce the time between generated output tokens [Checked claim 1155]. ai notis. https://ainotis.com/c/1155

Anyone may quote this address. It does not change; if we correct the story, this page says so.