GPT-6 Astra Pricing
Standard API rates, long-context multipliers, caching costs and a calculator for real workloads.
$10 / 1M input tokens · $1 / 1M cached input · $50 / 1M output tokens.
Standard token rates
| Token type | Price / 1M | Notes |
|---|---|---|
| Input | $10.00 | Standard uncached input |
| Cached input | $1.00 | Cache hit / reused input |
| Cache write | $12.50 | 1.25× uncached input rate |
| Output | $50.00 | Generated output tokens |
The >272K long-context rule
This matters for Astra because its context window is huge. OpenAI states that prompts with more than 272,000 input tokens are priced at 2× input and cache rates and 1.5× output rates for the full request.
Estimate your cost
Estimate GPT-6 Astra API cost
Enter token usage for a single request. Calculate separate requests individually; do not combine their token totals.
OpenAI states that prompts above 272K input tokens are billed at 2× input/cache rates and 1.5× output rates for the full request.
Estimate excludes tool-call fees and other service-specific charges.
Batch, Flex and Fast
OpenAI’s model page lists Batch and Flex at 50% of Standard rates, while Fast mode is priced at 2× the applicable rate. Tool-specific features may also add per-call fees, so token cost alone may not equal your final bill.
Frequently asked questions
How much is GPT-6 Astra per million tokens?
Standard API pricing is $10 per million input tokens, $1 per million cached input tokens and $50 per million output tokens.
Does GPT-6 Astra cost more for long context?
Yes. OpenAI says prompts above 272K input tokens use 2× input/cache rates and 1.5× output rates for the full request.
Is cached input cheaper?
Yes. The listed standard cached-input price is $1 per million tokens, compared with $10 per million uncached input tokens.
Primary sources
Specifications and prices can change. We prefer first-party documentation and record the date each page was reviewed.