OpenAI
GPT-6 Astra: price, context window, and caching
OpenAI's top GPT-6 model and its most expensive, aimed at the hardest long-running work that spans many tools, including coding.
Released September 3, 2026 · Prices as of September 28, 2026
In OpenAI’s words
“Our most capable model, built for the hardest end-to-end work”
What OpenAI says it’s good at
Facts
Specs and prices
| Fact | GPT-6 Astra |
|---|---|
| Maker | OpenAI |
| API model id | gpt-6-astra |
| Released | September 3, 2026 |
| Status | Current |
| Context window | 1.05M tokens |
| Max output | 128K tokens |
| Open weights | No |
| Input, per 1M tokens | $10 |
| Cache hit, per 1M | $1 |
| Cache write, per 1M | $12.50 |
| Output, per 1M tokens | $50 |
| Runs in | Codex, OpenCode, OpenRouter, and GitHub Copilot |
Standard API rates in US dollars, as published by the maker on September 28, 2026. Batch and priority tiers, taxes, and subscription plans are not included. GPT-6 Astra: Requests over 272K input tokens cost 2x for input and cache and 1.5x for output, for the whole request.
Good to know
- The default model in Codex CLI's bundled model list (version 0.158.0), where it starts at low reasoning effort.
- Available in the Codex app, CLI, and IDE extension, but not in Codex cloud.
- It accepts up to 922K input tokens of its context window.
Cost
What typical work costs
Example token counts at GPT-6 Astra’s published rates. On the agentic session, caching saves $17.00 against billing every token as ordinary input.
| Agentic coding session, 100K input, 400K written to cache, 2M read from cache, 50K output | $10.50 |
|---|---|
| Large one-off review, 150K input with no cache hits, 10K output | $2.00 |
| Output-heavy generation, 30K input, 80K output | $4.30 |
| A month of sessions, 110 sessions: 5 a day, 22 working days | $1,155.00 |
Prompt caching
How OpenAI bills cached tokens
OpenAI
Prompt caching is on by default. From GPT-5.6 on you can also mark up to four explicit cache breakpoints, while GPT-5.5 and earlier cache automatically only.
From GPT-5.6 on, a cache write costs 1.25x the uncached input price and a cache hit costs 0.1x. GPT-5.5 and earlier add no charge for writing the cache: written tokens are billed as ordinary input, and a hit costs 0.1x on the models compared here.
On GPT-5.6 and later, a cached prefix stays reusable for at least 30 minutes after its last use, and caching starts at 1,024 input tokens.
Source: OpenAI: Prompt caching
GPT-6 Astra compared
Claude Fable 5.1 vs GPT-6 Astra
Claude Fable 5.1 and GPT-6 Astra share $10 input and $50 output prices, and a cached coding session costs $10.50 on each. Caching decides which way it tips.
Claude Opus 5.5 vs GPT-6 Astra
Claude Code defaults to Claude Opus 5.5 and Codex CLI to GPT-6 Astra. Astra costs 2.5x more per token and 2.4x more on a cached coding session. Here is why.
Claude Sonnet 5 vs GPT-6 Astra
GPT-6 Astra charges 5x Claude Sonnet 5's rates on every kind of token. One cached coding session costs $10.50 against $2.40, a 4.4x gap. Here is why.
GPT-6 Astra vs Gemini 3.1 Pro Preview
GPT-6 Astra costs 5.3x as much as Gemini 3.1 Pro Preview on a cached coding session. How OpenAI's write premium, long-context tiers, and output caps compare.
GPT-6 Astra vs Gemini 3.8 Flash
GPT-6 Astra and Gemini 3.8 Flash launched a day apart at opposite ends of the price range, 14.8x apart on a cached coding session. What each is built for.
GPT-6 Astra vs GPT-5.5
GPT-6 Astra doubles GPT-5.5's input price and adds a 1.25x cache-write charge GPT-5.5 never had. What that does to agentic sessions and to Codex.
GPT-6 Astra vs GPT-6 Luna
GPT-6 Astra and GPT-6 Luna sit at opposite ends of OpenAI's lineup, 100x apart per token. What each is for, and where GPT-6 Sol fits between them.
GPT-6 Astra vs GPT-6 Sol
GPT-6 Astra costs 5x as much as GPT-6 Sol on every token, cached or not. What OpenAI built each for, which one Codex picks, and what a session costs.
Kimi K3 vs GPT-6 Astra
GPT-6 Astra costs 3.3x Kimi K3 per token and 3.7x on an agentic coding session, $10.50 against $2.85. What each maker claims for its top model.
Your own numbers
See what GPT-6 Astra really costs you.
everyaitoken reads your Codex, OpenCode, and OpenRouter history on your Mac and prices every request at API rates, with what caching saved or cost. $9 once.