Today ainotis Join

My notis

ModelsPublished All news from that day

Ongoing case: OpenAI's models 18 storiesSdkb / Selena Deckelmann at Wikimania 2025 / CC BY-SA 4.0, cropped

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

OpenAI's changelog dates it 8 October. Ultrafast is the API's fastest service tier; for GPT-6.1 Sol it is priced at $12 per million input tokens and $60 output at short context.

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

Share

Check our sources · 13 facts from 3 sources

OpenAI's API changelog for 8 October 2026 says Ultrafast mode is added for GPT-6.1 Sol in the Responses API. A request sets the model to gpt-6.1-sol and the service tier to ultrafast, which OpenAI says reduces the time between generated output tokens.

OpenAI says it is available to all API users, subject to rate limits, with global processing and US and EU data residency. Its guide calls Ultrafast the fastest service tier in the API, says it is available for GPT-6 Astra and GPT-6.1 Sol, and says to use it when speed justifies the higher cost.

The pricing page lists gpt-6.1-sol on Ultrafast at $12.00 per million input tokens, $0.60 cached input and $60.00 output at short context, and $24.00, $1.20 and $90.00 at long context. The same page lists Standard at $2.00, $0.10 and $10.00 at short context. For GPT-6 Astra, Ultrafast is $60.00 input and $300.00 output at short context.

The guide says Ultrafast has separate rate limits from Standard and Fast modes; for GPT-6.1 Sol they are 1,000,000 tokens per minute at the Build tier, 4,000,000 at Launch and 40,000,000 at Grow. It gives no tokens-per-second figure. Astra's Ultrafast supports US data residency and global processing only. The guide strongly recommends WebSockets, especially for agents that make many tool calls in quick succession.

Share this story

Your reaction

We count reactions per story and day, never who reacted. The counts help us choose what goes in the monthly issue. If you are signed in, your own page shows yours too.

Check our sources

Every sentence above is checked against these 3 sources.

1 OpenAI API changelogOpenAI · 8 Oct 2026 · 3 facts Open the source archived copy

  1. OpenAI API changelog, 8 October 2026: Ultrafast mode added for GPT-6.1 Sol in the Responses API.

    Toned down to what the source says
    Added [Ultrafast mode](https://developers.openai.com/api/docs/guides/ultrafast-mode) for [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol) in the Responses API.
    cite

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

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

  3. The changelog says Ultrafast for GPT-6.1 Sol is available to all API users, subject to rate limits, with global processing and US and EU data residency.

    It is available to all API users, subject to rate limits, with global processing and US and EU data residency.
    cite
2 Ultrafast mode | OpenAI APIOpenAI · 6 facts Open the source archived copy

  1. OpenAI's guide says Ultrafast mode is the fastest service tier in the OpenAI API, broadly available for GPT-6 Astra and GPT-6.1 Sol, to use when speed justifies the higher cost.

    Ultrafast mode is the fastest service tier in the OpenAI API. It is broadly available for GPT-6 Astra and GPT-6.1 Sol. Use it when speed justifies the higher cost.
    cite

  2. OpenAI's guide says Ultrafast has separate rate limits from Standard and Fast modes.

    Ultrafast has separate rate limits from Standard and Fast modes.
    cite

  3. OpenAI's guide says it strongly recommends WebSockets, especially for agentic applications that make many tool calls in quick succession.

    We strongly recommend WebSockets, especially for agentic applications that make many tool calls in quick succession.
    cite

  4. OpenAI's Ultrafast guide says: "GPT-6.1 Sol supports US and EU data residency and global processing. GPT-6 Astra Ultrafast supports US data residency and global processing only."

    Ultrafast mode for GPT-6.1 Sol supports US and EU data residency and global processing. GPT-6 Astra Ultrafast supports US data residency and global processing only.
    cite

  5. The guide lists Ultrafast rate limits for gpt-6.1-sol of 1,000,000 tokens per minute at the Build tier, 4,000,000 at Launch and 40,000,000 at Grow.

    Build | 1,000,000
    cite

  6. The guide gives no tokens-per-second figure for Ultrafast; it calls it the fastest service tier without stating a speed.

    Ultrafast mode is the fastest service tier in the OpenAI API.
    cite
3 Pricing | OpenAI APIOpenAI · 4 facts Open the source archived copy

  1. OpenAI's pricing page lists gpt-6.1-sol under Ultrafast, short context, at $12.00 per million input tokens, $0.60 cached input and $60.00 output.

    gpt-6.1-sol | $12.00 | $0.60 | $60.00 | $24.00 | $1.20 | $90.00
    cite

  2. OpenAI's pricing page lists gpt-6.1-sol under Ultrafast, long context, at $24.00 per million input tokens, $1.20 cached input and $90.00 output.

    gpt-6.1-sol | $12.00 | $0.60 | $60.00 | $24.00 | $1.20 | $90.00
    cite

  3. For comparison the pricing page lists gpt-6.1-sol at Standard, short context, at $2.00 per million input tokens, $0.10 cached input and $10.00 output.

    gpt-6.1-sol | $2.00 | $0.10 | $10.00 | $4.00 | $0.20 | $15.00
    cite

  4. The pricing page lists gpt-6-astra under Ultrafast, short context, at $60.00 per million input tokens, $6.00 cached input and $300.00 output.

    gpt-6-astra | $60.00 | $6.00 | $300.00 | $120.00 | $12.00 | $450.00
    cite

Topics

The morning email

On the mornings we publish: the three top stories and up to four short ones. Free.

We email you a link to confirm. An issue may include one sponsor, always labelled Sponsored · Advertisement. Our emails count opens and clicks, not who made them. Unsubscribe in one click. What we keep