OpenAI adds Ultrafast mode for GPT-6 Astra
OpenAI added Ultrafast mode for GPT-6 Astra in the Responses API to lower output token latency.
On Zabio today
gpt-6-astraLive. Call it by name, or let auto pick it when it fits the job.Price and details
What changed
OpenAI added Ultrafast mode for GPT-6 Astra in the Responses API. Developers can use gpt-6-astra with service_tier: “ultrafast” to reduce the time between generated output tokens. The mode is available to API customers, subject to rate limits, with global processing and US data residency. EU and other regional inference residency are not supported.
Source
Added Ultrafast mode for GPT-6 Astra in the Responses API. Use gpt-6-astra with service_tier: “ultrafast” to reduce the time between generated output tokens.
Original announcement: OpenAI API changelog
How it compares
The models in this story next to models of the same class at a similar price, all available with one Zabio key.
| Model | Input, $/M | Output, $/M | Cached, $/M | Context window | 1,000 calls | Analysis and reasoning, hard |
|---|---|---|---|---|---|---|
gpt-6-astraOpenAIIn this story | 10.00 | 50.00 | 1.00 | 400,000 | $45.00 | 93.0 |
claude-fable-5Anthropic | 10.00 | 50.00 | 1.00 | 1,000,000 | $45.00 | 78.8 |
claude-fable-5-1Anthropic | 10.00 | 50.00 | 0.25 | 1,000,000 | $45.00 | 90.1 |
gpt-4-turboOpenAI | 10.00 | 30.00 | no data | 128,000 | $35.00 | 46.6 |
Prices are the vendor list prices in USD per million tokens. "1,000 calls" is 1,000 requests of 2,000 input tokens and 500 output tokens each, without caching. Zabio bills the list price plus its service fee: see pricing.
Scores: percent correct for that kind of job, aggregated from public results by Epoch AI, LMArena, and LiveBench, read on 16 November 2026. Epoch AI: CC BY 4.0, LMArena: CC BY 4.0, LiveBench: Leaderboard results used with attribution; the 2.0 release states no terms of its own (read 2026-11-06); the first version's Mathematics, Language, IF results: Code Apache 2.0 and MIT; leaderboard results used with attribution
Source: OpenAI API changelog (2026-09-29)