gpt-5.6-terra pricing

gpt-5.6-terra by OpenAI is sold on OpenAI API, Amazon Bedrock and Microsoft Foundry (Azure), at the same lowest price on each: $2.00 per million input tokens and $12.00 per million output tokens. Batch, cache and in-region prices differ below.

Price on each platform

PlatformInputOutputCached inputBatch input / output
OpenAI API$2.00$12.00$0.20$1.00 / $6.00
Amazon Bedrock$2.00$12.00$0.20–
Microsoft Foundry (Azure)$2.00$12.00$0.20–

The lowest standard price on each platform, in USD per 1M tokens.

OpenAI API

TierRuns inInputOutputCached inputCache write
StandardAnywhere$2.00$12.00$0.20$2.50 (1h $5.00)
Standard · long promptsAnywhere$4.00$18.00$0.40$5.00 (1h $10.00)
BatchAnywhere$1.00$6.00$0.10$1.25 (1h $2.50)
Batch · long promptsAnywhere$2.00$9.00$0.20$2.50 (1h $5.00)
FlexAnywhere$1.00$6.00$0.10$1.25 (1h $2.50)
Flex · long promptsAnywhere$2.00$9.00$0.20$2.50 (1h $5.00)
PriorityAnywhere$4.00$24.00$0.40$5.00 (1h $10.00)
Priority · long promptsAnywhere$8.00$36.00$0.80$10.00 (1h $20.00)

Amazon Bedrock

TierRuns inInputOutputCached inputCache write
StandardGlobal (32 regions)$2.00$12.00$0.20$2.50
StandardIn region (8 regions)$2.20$13.20$0.22$2.75

Microsoft Foundry (Azure)

TierRuns inInputOutputCached inputCache write
StandardGlobal (25 regions)$2.00$12.00$0.20$2.50
Standard · long promptsGlobal (25 regions)$4.00$18.00$0.40$5.00
StandardGeography (data zone) (13 regions)$2.20$13.20$0.22$2.75
Standard · long promptsGeography (data zone) (13 regions)$4.40$19.80$0.44$5.50
FlexGlobal (25 regions)$1.00$6.00$0.10$1.25
Flex · long promptsGlobal (25 regions)$2.00$9.00$0.20$2.50
PriorityGlobal (24 regions)$4.00$24.00$0.40$5.00
Priority · long promptsGlobal (25 regions)$8.00$36.00$0.80$10.00
PriorityGeography (data zone) (13 regions)$4.40$26.40$0.44$5.50
Priority · long promptsGeography (data zone) (13 regions)$8.80$39.60$0.88$11.00

More OpenAI models

Prices in USD per 1 million tokens, from OpenAI and Anthropic's pricing pages, the AWS Price List API (Bedrock) and the Azure Retail Prices API (Microsoft Foundry). Cloud prices are the lowest in any region; global deployments can run anywhere.

Prices as of 12 Nov 2026. All AI models