Qwen3 Coder 480B A35B Instruct

Qwen · Active · available in 7 of 16 regions

Batch inferenceStreaming Tool useVisionPrompt cachingEmbeddingsFine-tuning
Context window
Max output
Input / 1M
$0.450
us-west-2
Output / 1M
$1.80

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) $0.450 $1.80 $0.225 $0.900 API
us-west-2 US West (Oregon) $0.450 $1.80 $0.225 $0.900 API
eu-west-2 EU (London) $0.700 $2.79 $0.350 $1.40 API
eu-north-1 EU (Stockholm) $0.450 $1.80 $0.225 $0.900 API
ap-southeast-2 Asia Pacific (Sydney) $0.463 $1.85 $0.232 $0.927 API
ap-northeast-1 Asia Pacific (Tokyo) $0.540 $2.18 $0.270 $1.09 API
ap-south-1 Asia Pacific (Mumbai) $0.530 $2.12 $0.265 $1.06 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 Qwen3 Coder 480B A35B Instruct cost on Amazon Bedrock?
$0.450 per 1M input tokens and $1.80 per 1M output tokens in us-west-2. The cheapest region is us-east-2 at $0.450.
Which AWS regions support Qwen3 Coder 480B A35B Instruct?
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 Qwen3 Coder 480B A35B Instruct on Bedrock?
qwen.qwen3-coder-480b-a35b-v1:0.

Other Qwen models