Back to models
available
GPT-6 Astra Pro
venice/openai-gpt-6-astra-proPrices
- Input
$12.50 per 1M tokens
low- Input (>272k ctx)
$25.00 per 1M tokens
low- Input (cache write, >272k ctx)
$31.25 per 1M tokens
low- Input (cache write)
$15.63 per 1M tokens
low- Input (cached read, >272k ctx)
$2.50 per 1M tokens
low- Input (cached read)
$1.25 per 1M tokens
low- Output
$62.50 per 1M tokens
low- Output (>272k ctx)
$93.75 per 1M tokens
low
Specifications
- Provider
- venice
- Context window
- 1,050,000
- Max output tokens
- 128,000
- Open weights
- no
- Released
- 09/05/2026
- Retires
- no date announced
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 12.5 per 1M tokens, unchanged since 09/14/2026
- Output
- 62.5 per 1M tokens, unchanged since 09/14/2026
- Input (cached read)
- 1.25 per 1M tokens, unchanged since 09/14/2026
- Input (cache write)
- 15.63 per 1M tokens, unchanged since 09/14/2026
- Input (>272k ctx)
- 25 per 1M tokens, unchanged since 09/14/2026
- Output (>272k ctx)
- 93.75 per 1M tokens, unchanged since 09/14/2026
- Input (cached read, >272k ctx)
- 2.5 per 1M tokens, unchanged since 09/14/2026
- Input (cache write, >272k ctx)
- 31.25 per 1M tokens, unchanged since 09/14/2026