DeepSeek-V3.1

DeepSeek · Active · available in 7 of 16 regions

Batch inferenceStreaming Tool useVisionPrompt cachingEmbeddingsFine-tuning
Context window
Max output
Input / 1M
$0.580
us-west-2
Output / 1M
$1.68

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-2 US East (Ohio) $0.580 $1.68 $0.290 $0.840 API
us-west-2 US West (Oregon) $0.580 $1.68 $0.290 $0.840 API
eu-west-2 EU (London) $0.900 $2.61 $0.450 $1.30 API
eu-north-1 EU (Stockholm) $0.580 $1.68 $0.290 $0.840 API
ap-southeast-2 Asia Pacific (Sydney) $0.597 $1.73 $0.299 $0.865 API
ap-northeast-1 Asia Pacific (Tokyo) $0.702 $2.03 $0.351 $1.02 API
ap-south-1 Asia Pacific (Mumbai) $0.682 $1.98 $0.341 $0.988 API

Region availability

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.

Common questions

How much does DeepSeek-V3.1 cost on Amazon Bedrock?
$0.580 per 1M input tokens and $1.68 per 1M output tokens in us-west-2. The cheapest region is us-east-2 at $0.580.
Which AWS regions support DeepSeek-V3.1?
7 of 16 regions: us-east-2, us-west-2, eu-west-2, eu-north-1, ap-southeast-2, ap-northeast-1, ap-south-1.
What is the model ID for DeepSeek-V3.1 on Bedrock?
deepseek.v3-v1:0.

Other DeepSeek models