DeepSeek v3.2 pricing
DeepSeek v3.2 by DeepSeek is sold on Amazon Bedrock and Microsoft Foundry (Azure). It costs $0.62 per million input tokens and $1.85 per million output tokens on Amazon Bedrock (in us-east-1); $0.58 per million input tokens and $1.68 per million output tokens on Microsoft Foundry (Azure) (global deployment).
Price on each platform
| Platform | Input | Output | Cached input | Batch input / output |
|---|---|---|---|---|
| Amazon Bedrock | $0.62 | $1.85 | – | $0.31 / $0.925 |
| Microsoft Foundry (Azure) | $0.58 | $1.68 | – | – |
The lowest standard price on each platform, in USD per 1M tokens.
Amazon Bedrock
| Tier | Runs in | Input | Output |
|---|---|---|---|
| Standard | In region (us-east-1, us-east-2, us-west-2) | $0.62 | $1.85 |
| Standard | In region (ap-southeast-2) | $0.64 | $1.91 |
| Standard | In region (8 regions) | $0.74 | $2.22 |
| Standard | In region (eu-west-2) | $0.961 | $2.8675 |
| Batch | In region (us-east-1, us-east-2, us-west-2) | $0.31 | $0.925 |
| Batch | In region (ap-southeast-2) | $0.32 | $0.955 |
| Batch | In region (8 regions) | $0.37 | $1.11 |
| Batch | In region (eu-west-2) | $0.4805 | $1.4338 |
| Flex | In region (us-east-1, us-east-2, us-west-2) | $0.31 | $0.925 |
| Flex | In region (ap-southeast-2) | $0.32 | $0.955 |
| Flex | In region (8 regions) | $0.37 | $1.11 |
| Flex | In region (eu-west-2) | $0.4805 | $1.4338 |
| Priority | In region (us-east-1, us-east-2, us-west-2) | $1.085 | $3.2375 |
| Priority | In region (ap-southeast-2) | $1.12 | $3.3425 |
| Priority | In region (8 regions) | $1.295 | $3.885 |
| Priority | In region (eu-west-2) | $1.6818 | $5.0181 |
Microsoft Foundry (Azure)
| Tier | Runs in | Input | Output |
|---|---|---|---|
| Standard | Global (40 regions) | $0.58 | $1.68 |
| Standard | Geography (data zone) (39 regions) | $0.64 | $1.85 |
More DeepSeek models
DeepSeek V3.1 · deepseek-r1 · deepseek-v3 · deepseek-v3-0324 · deepseek-v3.2-sp · deepseek-v4-flash · deepseek-v4-flash-0731 · deepseek-v4-pro · deepseek-v4.1-flash · R1
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