Llama 4 Scout API Pricing

Llama 4 Scout by Meta costs $0.17 per million input tokens and $0.66 per million output tokens on AWS Bedrock.

Price verified from AWS Bedrock's pricing page.

Rates and limits

Input / 1M
$0.17
Output / 1M
$0.66
Cached input / 1M
Not listed
Batch discount
50% off
Context window
328K tokens
Released
February 2026

Pricing note: Open-weight model; price is AWS Bedrock on-demand in US East (N. Virginia), from the AWS Price List API ($0.00017 / $0.00066 per 1K input/output tokens; batch $0.000085 / $0.00033). Together AI removed Llama 4 Scout from serverless on 2026-02-06. DeepInfra lists it at $0.10 / $0.30.

What Llama 4 Scout costs per month

Token volume split 3:1 between input and output, with no prompt caching.

Tokens per monthInput / outputStandardBatch API
1M750K / 250K$0.29$0.15
10M7.5M / 2.5M$2.93$1.46
100M75M / 25M$29.25$14.63
Estimate your own workload with Llama 4 Scout

Where to run Llama 4 Scout

Prices above are AWS Bedrock's rates. Other platforms can charge differently; the cloud platform view compares them.

Llama 4 Scout pricing FAQ

How much does Llama 4 Scout cost per million tokens?

Llama 4 Scout costs $0.17 per million input tokens and $0.66 per million output tokens, as listed on AWS Bedrock's pricing page on September 30, 2026.

How much does Llama 4 Scout cost for 10 million tokens a month?

About $2.93 a month, assuming 7.5 million input and 2.5 million output tokens with no prompt caching, or $1.46 through the batch API.

What is the context window of Llama 4 Scout?

Llama 4 Scout accepts up to 327,680 tokens of context.

Does Llama 4 Scout support prompt caching?

No cached-input price is listed for Llama 4 Scout, so repeated prompt prefixes are billed at the standard input rate.

Is there a batch discount for Llama 4 Scout?

Yes. Requests sent through the batch API cost 50% less: $0.085 per million input tokens and $0.33 per million output tokens.

Where can I use the Llama 4 Scout API?

Llama 4 Scout is available through AWS Bedrock and OpenRouter.

Prices shown as input / output per million tokens. All model prices · Side-by-side comparison