Amazon Bedrock
GPT-6.2 Astra (US)
A frontier reasoning model for coding, computer use, and professional work such as slides, spreadsheets, and documents.
us.openai.gpt-6.2-astraContext
1.1M
Max output
128K
Input $/M
$8.80
Output $/M
$44.00
Cache read $/M
$0.44
Cache write $/M
$11.00
Against the catalogue
Context window1.1M
Larger than 99% of the 10,022 models listed
Input price$8.80
Cheaper than 4% of priced models
Capabilities
Reasoningsupported
Tool callingsupported
Structured outputsupported
Attachmentssupported
Temperaturenot supported
Open weightsnot supported
Interleaved thinkingnot supported
Modalities
Input
TextImage
Output
Text
Reasoning controls
effortlow, medium, high, xhigh, maxPricing detail
| Rate | Base $/M | Over 200K $/M |
|---|---|---|
| Input | $8.80 | $17.60 |
| Output | $44.00 | $66.00 |
| Cache read | $0.44 | $0.88 |
| Cache write | $11.00 | $22.00 |
Tiers
- context ≥ 272K$17.60 in / $66.00 out
Experimental modes
ultrafastEnable with
body.additionalModelRequestFields.service_tierultrafast