GPT-6.2 Astra
OpenAI's most capable model for the hardest projects, from complex coding and computer use to finished documents, slides, and spreadsheets.
- Input price
- $7.20–$14.40list $8.00-10%
- Output price
- $36.00–$54.00list $40.00-10%
- Context
- 1.1M
- Max output
- 128K
- 30-day uptime
- —
- Released
- 2026-11-17
- Knowledge cutoff
- 2026-05-18
InputTextImagePDFOutputText
Providers
This model is served by the dedicated providers below. We pick the provider for each request, so provider preferences don’t apply, including a provider named in your request. Prices in USD per 1M tokens. Need a custom setup? Contact [email protected].
Included providers1
- SuccessTTFT
- OpenAIUnited States——
Pricing
Prices for this model. Each request is billed at these prices, whichever provider serves it.
| Item | Standard | Batch | Priority | ultrafast | Price |
|---|---|---|---|---|---|
| Prompt ≤ 272K tokensuntil 2027-03-01 | |||||
| Inputper 1M tokens | $7.20list $8.00-10% | $3.60list $4.00-10% | $14.40list $16.00-10% | $21.60list $24.00-10% | — |
| Outputper 1M tokens | $36.00list $40.00-10% | $18.00list $20.00-10% | $72.00list $80.00-10% | $108.00list $120.00-10% | — |
| Cache readper 1M tokens | $0.36list $0.40-10% | $0.18list $0.20-10% | $0.72list $0.80-10% | $1.08list $1.20-10% | — |
| Cache write (5 min)per 1M tokens | $9.00list $10.00-10% | $4.50list $5.00-10% | $18.00list $20.00-10% | $27.00list $30.00-10% | — |
| Cache write (1 hour)per 1M tokens | $18.00list $20.00-10% | $9.00list $10.00-10% | $36.00list $40.00-10% | $54.00list $60.00-10% | — |
| Prompt > 272K tokensuntil 2027-03-01 | |||||
| Inputper 1M tokens | $14.40list $16.00-10% | $7.20list $8.00-10% | $28.80list $32.00-10% | $43.20list $48.00-10% | — |
| Outputper 1M tokens | $54.00list $60.00-10% | $27.00list $30.00-10% | $108.00list $120.00-10% | $162.00list $180.00-10% | — |
| Cache readper 1M tokens | $0.72list $0.80-10% | $0.36list $0.40-10% | $1.44list $1.60-10% | $2.16list $2.40-10% | — |
| Cache write (5 min)per 1M tokens | $18.00list $20.00-10% | $9.00list $10.00-10% | $36.00list $40.00-10% | $54.00list $60.00-10% | — |
| Cache write (1 hour)per 1M tokens | $36.00list $40.00-10% | $18.00list $20.00-10% | $72.00list $80.00-10% | $108.00list $120.00-10% | — |
| Prompt ≤ 272K tokensfrom 2027-03-01 | |||||
| Inputper 1M tokens | $7.20list $8.00-10% | $3.60list $4.00-10% | $14.40list $16.00-10% | $43.20list $48.00-10% | — |
| Outputper 1M tokens | $36.00list $40.00-10% | $18.00list $20.00-10% | $72.00list $80.00-10% | $216.00list $240.00-10% | — |
| Cache readper 1M tokens | $0.36list $0.40-10% | $0.18list $0.20-10% | $0.72list $0.80-10% | $2.16list $2.40-10% | — |
| Cache write (5 min)per 1M tokens | $9.00list $10.00-10% | $4.50list $5.00-10% | $18.00list $20.00-10% | $54.00list $60.00-10% | — |
| Cache write (1 hour)per 1M tokens | $18.00list $20.00-10% | $9.00list $10.00-10% | $36.00list $40.00-10% | $108.00list $120.00-10% | — |
| Prompt > 272K tokensfrom 2027-03-01 | |||||
| Inputper 1M tokens | $14.40list $16.00-10% | $7.20list $8.00-10% | $28.80list $32.00-10% | $86.40list $96.00-10% | — |
| Outputper 1M tokens | $54.00list $60.00-10% | $27.00list $30.00-10% | $108.00list $120.00-10% | $324.00list $360.00-10% | — |
| Cache readper 1M tokens | $0.72list $0.80-10% | $0.36list $0.40-10% | $1.44list $1.60-10% | $4.32list $4.80-10% | — |
| Cache write (5 min)per 1M tokens | $18.00list $20.00-10% | $9.00list $10.00-10% | $36.00list $40.00-10% | $108.00list $120.00-10% | — |
| Cache write (1 hour)per 1M tokens | $36.00list $40.00-10% | $18.00list $20.00-10% | $72.00list $80.00-10% | $216.00list $240.00-10% | — |
| Web searchper request | — | — | — | — | $0.009list $0.01-10% |
| Estimated cost of common use (500 output tokens each) | |||||
| One chat message3K input tokens | $0.0396 | — | $0.0792 | $0.119 | — |
| Agent first turn100K tokens of context, none cached | $0.918 | — | $1.84 | $2.75 | — |
| Each later agent turncontext read from cache, plus 2K new tokens | $0.072 | — | $0.144 | $0.216 | — |
| 20-turn agent taskfirst turn plus 19 more | $2.29 | — | $4.57 | $6.86 | — |
Try it
Runs on your balance and is billed like any API request.
Similar models
Other models with the same output types at a similar price.