GPT-6 Astra (Reseller)
GPT-6 Astra for Codex (Responses API).
- Input price
- $1.00–$2.00list $10.00-90%
- Output price
- $5.00–$7.50list $50.00-90%
- Context
- 272K
- Max output
- 128K
- 30-day uptime
- —
- Released
- 2026-09-03
- Knowledge cutoff
- 2026-04-30
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 | Standard Discount | Flex | Flex Discount | Batch | Batch Discount | Priority | Priority Discount | ultrafast | ultrafast Discount | Price | Price Discount | ||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Prompt ≤ 272K tokens | ||||||||||||||||||
| Inputper 1M tokens | $1.00 | list $10.00 | -90% | $0.50 | list $5.00 | -90% | $0.50 | list $5.00 | -90% | $2.00 | list $20.00 | -90% | $6.00 | list $60.00 | -90% | — | ||
| Outputper 1M tokens | $5.00 | list $50.00 | -90% | $2.50 | list $25.00 | -90% | $2.50 | list $25.00 | -90% | $10.00 | list $100.00 | -90% | $30.00 | list $300.00 | -90% | — | ||
| Cache readper 1M tokens | $0.10 | list $1.00 | -90% | $0.05 | list $0.50 | -90% | $0.05 | list $0.50 | -90% | $0.20 | list $2.00 | -90% | $0.60 | list $6.00 | -90% | — | ||
| Cache write (5 min)per 1M tokens | $1.25 | list $12.50 | -90% | $0.625 | list $6.25 | -90% | $0.625 | list $6.25 | -90% | $2.50 | list $25.00 | -90% | $7.50 | list $75.00 | -90% | — | ||
| Cache write (1 hour)per 1M tokens | $2.50 | list $25.00 | -90% | $1.25 | list $12.50 | -90% | $1.25 | list $12.50 | -90% | $5.00 | list $50.00 | -90% | $15.00 | list $150.00 | -90% | — | ||
| Prompt > 272K tokens | ||||||||||||||||||
| Inputper 1M tokens | $2.00 | list $20.00 | -90% | $1.00 | list $10.00 | -90% | $1.00 | list $10.00 | -90% | $4.00 | list $40.00 | -90% | $12.00 | list $120.00 | -90% | — | ||
| Outputper 1M tokens | $7.50 | list $75.00 | -90% | $3.75 | list $37.50 | -90% | $3.75 | list $37.50 | -90% | $15.00 | list $150.00 | -90% | $45.00 | list $450.00 | -90% | — | ||
| Cache readper 1M tokens | $0.20 | list $2.00 | -90% | $0.10 | list $1.00 | -90% | $0.10 | list $1.00 | -90% | $0.40 | list $4.00 | -90% | $1.20 | list $12.00 | -90% | — | ||
| Cache write (5 min)per 1M tokens | $2.50 | list $25.00 | -90% | $1.25 | list $12.50 | -90% | $1.25 | list $12.50 | -90% | $5.00 | list $50.00 | -90% | $15.00 | list $150.00 | -90% | — | ||
| Cache write (1 hour)per 1M tokens | $5.00 | list $50.00 | -90% | $2.50 | list $25.00 | -90% | $2.50 | list $25.00 | -90% | $10.00 | list $100.00 | -90% | $30.00 | list $300.00 | -90% | — | ||
| Web searchper request | — | — | — | — | — | $0.001 | list $0.01 | -90% | ||||||||||
| Estimated cost of common use (500 output tokens each) | ||||||||||||||||||
| One chat message3K input tokens | $0.0055 | $0.00275 | — | $0.011 | $0.033 | — | ||||||||||||
| Agent first turn100K tokens of context, none cached | $0.128 | $0.0638 | — | $0.255 | $0.765 | — | ||||||||||||
| Each later agent turncontext read from cache, plus 2K new tokens | $0.015 | $0.0075 | — | $0.03 | $0.09 | — | ||||||||||||
| 20-turn agent taskfirst turn plus 19 more | $0.412 | $0.206 | — | $0.825 | $2.48 | — | ||||||||||||
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.