Skip to content

GPT-6 Astra

OpenAI's most capable model, for the hardest work

By OpenAIsource

Facts read from official pages, last on

Official page

Price

What the gateway charges per million tokens: what you send in, and what the model writes back.

Source: Vercel AI Gateway, checked 2026-09-26.

Input
$10per 1M tokens
Output
$50per 1M tokensOutput costs 5x the input.

Above 272,000 input tokens: $20 in, $75 out per 1M.

Specs

How much it reads at once, how much it writes back, and how recent its knowledge is.

Source: Vercel AI Gateway, checked 2026-09-26.

Context window
1.05M tokens1,050,000
Max output
128K tokens128,000
Knowledge cutoff
Apr 30, 2026
Released
Type
Language
Modalities
Takes text, image, PDF. Returns text.
Gateway ID
openai/gpt-6-astra

Capabilities

What the gateway says this model supports.

Source: Vercel AI Gateway, checked 2026-09-26.

  • File input
  • Implicit caching
  • Reasoning
  • Tool use
  • Vision
  • Web search
  • Websocket realtime
  • Explicit caching
  • Structured output
  • Fast

Data handling

What happens to your prompts, and what you have to switch on.

Source: Vercel AI Gateway, checked 2026-09-26.

ZDRSome providers

Zero data retention

Available on a paid Vercel plan through the AI Gateway, from some providers on it (you turn it on).

NTEvery provider

No training on prompts

Offered by every provider on the Vercel AI Gateway, when you turn it on.

Also by OpenAI4

Friday

The brief, by email

Five to seven links an issue, each with what to do about it.

Unsubscribe from any issue.

This page as Markdown