GPT-6.2 Astra (Reseller)
GPT-6.2 Astra for Codex (Responses API).
- Input price
- $0.80–$1.60list $8.00-90%
- Output price
- $4.00–$6.00list $40.00-90%
- Context
- 272K
- Max output
- 128K
- 30-day uptime
- —
- Released
- 2026-11-17
- Knowledge cutoff
- 2026-05-18
InputTextImageOutputText
Providers
Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.
Pricing
All prices for this model, by service tier.
| Item | Standard | Batch | Priority | ultrafast | Price |
|---|---|---|---|---|---|
| Prompt ≤ 272K tokens | |||||
| Inputper 1M tokens | $0.80list $8.00-90% | $0.40list $4.00-90% | $1.60list $16.00-90% | $4.80list $48.00-90% | — |
| Outputper 1M tokens | $4.00list $40.00-90% | $2.00list $20.00-90% | $8.00list $80.00-90% | $24.00list $240.00-90% | — |
| Cache readper 1M tokens | $0.04list $0.40-90% | $0.02list $0.20-90% | $0.08list $0.80-90% | $0.24list $2.40-90% | — |
| Cache write (5 min)per 1M tokens | $1.00list $10.00-90% | $0.50list $5.00-90% | $2.00list $20.00-90% | $6.00list $60.00-90% | — |
| Cache write (1 hour)per 1M tokens | $2.00list $20.00-90% | $1.00list $10.00-90% | $4.00list $40.00-90% | $12.00list $120.00-90% | — |
| Prompt > 272K tokens | |||||
| Inputper 1M tokens | $1.60list $16.00-90% | $0.80list $8.00-90% | $3.20list $32.00-90% | $9.60list $96.00-90% | — |
| Outputper 1M tokens | $6.00list $60.00-90% | $3.00list $30.00-90% | $12.00list $120.00-90% | $36.00list $360.00-90% | — |
| Cache readper 1M tokens | $0.08list $0.80-90% | $0.04list $0.40-90% | $0.16list $1.60-90% | $0.48list $4.80-90% | — |
| Cache write (5 min)per 1M tokens | $2.00list $20.00-90% | $1.00list $10.00-90% | $4.00list $40.00-90% | $12.00list $120.00-90% | — |
| Cache write (1 hour)per 1M tokens | $4.00list $40.00-90% | $2.00list $20.00-90% | $8.00list $80.00-90% | $24.00list $240.00-90% | — |
| Web searchper request | — | — | — | — | $0.001list $0.01-90% |
| Estimated cost of common use (500 output tokens each) | |||||
| One chat message3K input tokens | $0.0044 | — | $0.0088 | $0.0264 | — |
| Agent first turn100K tokens of context, none cached | $0.102 | — | $0.204 | $0.612 | — |
| Each later agent turncontext read from cache, plus 2K new tokens | $0.008 | — | $0.016 | $0.048 | — |
| 20-turn agent taskfirst turn plus 19 more | $0.254 | — | $0.508 | $1.52 | — |
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.