DeepSeek V3.2
DeepSeek · Active · available in 10 of 31 regions
Batch inferenceStreaming Tool useVisionPrompt cachingEmbeddingsFine-tuning
- Context window
- —
- Max output
- —
- Input / 1M
- $0.620
- us-east-1
- Output / 1M
- $1.85
What DeepSeek V3.2 is good for
editorialDeepSeek V3.2 at $0.620 per 1M input tokens. Callable in 10 of 31 regions.
Suits
- Bulk jobs. Batch inference is available, typically at half the on-demand rate, for work that can wait — backfills, nightly enrichment, evaluation runs.
Think twice if
- Agentic loops. No prompt caching published, so every step re-pays full price for the prompt prefix. Expensive for agents that resend a long context.
- Function calling. No tool use, so it cannot drive an agent loop or call your APIs — it answers from what is in the prompt.
- Documents with layout. Text only. Scanned PDFs, screenshots and charts need a vision model or an OCR step first.
This section is judgement, not data from AWS. It is composed from the capabilities, context window, price position and region coverage shown elsewhere on this page — so it stays in step with the daily snapshot rather than going stale.
Where teams typically use it
Coding
Writing, reviewing and refactoring code, usually across more than one file.
- · A review pass that flags real defects with a severity and leaves style alone.
- · A framework upgrade applied across a repository, one module at a time, tests green between each.
- · Turning a failing bug report into a reproducing test and then a fix.
Model & inference profile IDs
Base model ID — direct on-demand invoke
Pricing by region
USD per 1M tokens| Region | Input | Output | Cache read | Cache write | Batch in | Batch out | Source |
|---|---|---|---|---|---|---|---|
| us-east-1 US East (N. Virginia) | $0.620 | $1.85 | — | — | $0.310 | $0.925 | API |
| us-east-2 US East (Ohio) | $0.620 | $1.85 | — | — | $0.310 | $0.925 | API |
| us-west-2 US West (Oregon) | $0.620 | $1.85 | — | — | $0.310 | $0.925 | API |
| eu-west-2 EU (London) | $0.961 | $2.87 | — | — | $0.481 | $1.43 | API |
| eu-north-1 EU (Stockholm) | $0.740 | $2.22 | — | — | $0.370 | $1.11 | API |
| ap-northeast-1 Asia Pacific (Tokyo) | $0.740 | $2.22 | — | — | $0.370 | $1.11 | API |
| ap-south-1 Asia Pacific (Mumbai) | $0.740 | $2.22 | — | — | $0.370 | $1.11 | API |
| ap-southeast-2 Asia Pacific (Sydney) | $0.640 | $1.91 | — | — | $0.320 | $0.955 | API |
| ap-southeast-3 Asia Pacific (Jakarta) | $0.740 | $2.22 | — | — | $0.370 | $1.11 | API |
| sa-east-1 South America (Sao Paulo) | $0.740 | $2.22 | — | — | $0.370 | $1.11 | API |
Region availability
On-demand us-east-1 On-demand 100M TPM 10,000 RPM On-demand us-east-2 On-demand 100M TPM 10,000 RPM Not available us-west-1 Not available On-demand us-west-2 On-demand 100M TPM 10,000 RPM Not available ca-central-1 Not available Not available ca-west-1 Not available Not available mx-central-1 Not available Not available eu-west-1 Not available On-demand eu-west-2 On-demand 100M TPM 10,000 RPM Not available eu-west-3 Not available Not available eu-central-1 Not available Not available eu-central-2 Not available On-demand eu-north-1 On-demand 100M TPM 10,000 RPM Not available eu-south-1 Not available Not available eu-south-2 Not available Not available ap-east-2 Not available On-demand ap-northeast-1 On-demand 100M TPM 10,000 RPM Not available ap-northeast-2 Not available Not available ap-northeast-3 Not available On-demand ap-south-1 On-demand 100M TPM 10,000 RPM Not available ap-south-2 Not available Not available ap-southeast-1 Not available On-demand ap-southeast-2 On-demand 100M TPM 10,000 RPM On-demand ap-southeast-3 On-demand 100M TPM 10,000 RPM Not available ap-southeast-4 Not available Not available ap-southeast-5 Not available Not available ap-southeast-6 Not available Not available ap-southeast-7 Not available Not available il-central-1 Not available Not available af-south-1 Not available On-demand sa-east-1 On-demand 100M TPM 10,000 RPM
TPM / RPM are default account quotas from AWS Service Quotas where a model-specific limit is published. They are per-account defaults and adjustable on request.
Where this model actually runs
Under a strict residency constraint, DeepSeek V3.2 can be served without the request leaving 9 of the 25 jurisdictions with a Bedrock region.
DeepSeek V3.2 appears in
Common questions
- How much does DeepSeek V3.2 cost on Amazon Bedrock?
- $0.620 per 1M input tokens and $1.85 per 1M output tokens in us-east-1.
- Which AWS regions support DeepSeek V3.2?
- 10 of 31 regions: us-east-1, us-east-2, us-west-2, eu-west-2, eu-north-1, ap-northeast-1, ap-south-1, ap-southeast-2, ap-southeast-3, sa-east-1.
- What is the model ID for DeepSeek V3.2 on Bedrock?
- deepseek.v3.2.