OpenAI · API model
GPT-6 Astra
API id gpt-6-astra prices checked
- Input
- $10.00/1M
- Output
- $50.00/1M
- Context
- 1.05Mtokens
- Max output
- 128Ktokens
- Knowledge cutoff
- Apr 2026
- Typical request
- $0.035
Pricing
US dollars per 1 million tokens. A typical request (1,000 input + 500 output tokens) costs $0.035 at standard rates.
| Rate | Input | Cached input | Output |
|---|---|---|---|
| Standard | $10.00 | $1.00 | $50.00 |
| Long promptsPrompts over 272K tokens | $20.00 | $2.00 | $75.00 |
| BatchAsynchronous, results within 24 hours | $5.00 | — | $25.00 |
| FlexLower price, slower responses | $5.00 | — | $25.00 |
| PriorityFast mode, 2x standard. Ultrafast (6x, US data residency only) is also offered. | $20.00 | — | $100.00 |
Capabilities and limits
| Context window | 1.05M tokens |
|---|---|
| Max output | 128K tokens |
| Input | TextImages |
| Output | Text |
| Reasoning | Adjustable effort |
| Tool use | Yes |
| Structured output (JSON) | Yes |
| Knowledge cutoff | Apr 30, 2026 |
Lifecycle status
No deprecation or shutdown date announced on OpenAI's official deprecations page as of Oct 23, 2026.
Change history
Launches, price changes and retirements for GPT-6 Astra, newest first, each linked to the vendor's notice.
GPT-6.1 Sol released at $2 / $10 per 1M tokens; Ultrafast tier for GPT-6 Astra
6.1 Sol cuts cached input to $0.10. Astra Ultrafast costs $60 / $300 (6x standard), US data residency only.
vendorOpenAI API changelog
GPT-6 Astra released at $10 / $50 per 1M tokens
$20 / $75 above 272K input tokens. Batch and Flex at half price, Fast mode at double.
Benchmarks and speed
Not collected yet. Scores will come only from independent leaderboards, each shown with its source and test date.
Planned: GPQA Diamond, SWE-bench Verified, AIME 2025, LMArena Elo, output speed and time to first token.
Where these numbers come from
Every value is an observation with a source and a date. independent is a third-party catalog, vendor is the model maker's own page, derived is our calculation.
| Field | Value | Source | Observed |
|---|---|---|---|
| Standard price, input / output | $10.00 / $50.00 | vendorOpenAI API pricing | Oct 17, 2026 |
| Standard price, input / output | $10.00 / $50.00 | independentLiteLLM | Oct 17, 2026 |
| Standard price, input / output | $10.00 / $50.00 | independentOpenRouter | Oct 17, 2026 |
| Context window / max output | 1,050,000 / 128,000 tokens | vendorOpenAI model docs | Oct 17, 2026 |
| Release date | 2026-09-03 | vendorOpenAI API changelog | Oct 17, 2026 |
| Benchmarks at launch | Terminal-Bench 4.0 57.9%, OSWorld 2.0 72.6%, GPQA Diamond 96.0% (OpenAI's own figures) | vendorOpenAI launch post | Oct 17, 2026 |