Llama 4 Scout 17B Instruct

Meta · Active · available in 3 of 16 regions

VisionBatch inferenceStreaming Tool usePrompt cachingEmbeddingsFine-tuning
Context window
Max output
Input / 1M
$0.170
us-east-1
Output / 1M
$0.660

Model & inference profile IDs

Base model ID — direct on-demand invoke

Cross-region inference profiles (1)

Regions marked Inference profile only require a profile ID rather than the base model ID — invoking the base ID there returns a validation error. Regional (us., eu.) profiles carry a 10% premium over global.

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) $0.170 $0.660 $0.085 $0.330 API
us-east-2 US East (Ohio) $0.170 $0.660 $0.085 $0.330 API
us-west-2 US West (Oregon) $0.170 $0.660 $0.085 $0.330 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 Llama 4 Scout 17B Instruct cost on Amazon Bedrock?
$0.170 per 1M input tokens and $0.660 per 1M output tokens in us-east-1.
Which AWS regions support Llama 4 Scout 17B Instruct?
3 of 16 regions: us-east-1, us-east-2, us-west-2. Regions marked profile-only need a cross-region inference profile ID such as us.meta.llama4-scout-17b-instruct-v1:0 rather than the bare model ID.
What is the model ID for Llama 4 Scout 17B Instruct on Bedrock?
meta.llama4-scout-17b-instruct-v1:0. In regions where it is only reachable through a cross-region inference profile, use a prefixed ID instead: us.meta.llama4-scout-17b-instruct-v1:0.

Other Meta models