Meta

Llama 4 Scout API Pricing

Aggregator pricing; Meta does not sell a first-party priced API (llama.developer.meta.com is waitlist-only with no published pricing). Mixture-of-experts model, 17B active / 109B total parameters, 16 experts. Knowledge cutoff August 2024.

Verified against Meta’s pricing page on 2026-07-02.

View source ↗

Facts

Specs

  • FamilyLlama 4
  • API IDmeta-llama/llama-4-scout
  • ModalityMultimodal
  • Context window10M tokens
  • Max output
  • Release date2025-04-05

Pricing (per 1M tokens)

  • Input$0.10 / 1M tokens
  • Output$0.30 / 1M tokens
  • Cached input
  • Cache write
  • Batch discount

Capabilities

vision, tool-use, mixture-of-experts

Notes

Aggregator pricing; Meta does not sell a first-party priced API (llama.developer.meta.com is waitlist-only with no published pricing). Mixture-of-experts model, 17B active / 109B total parameters, 16 experts. Knowledge cutoff August 2024.

Worked cost examples

Estimated monthly cost on three common usage shapes

WorkloadEst. monthly cost

Chatbot

800 input / 200 output tokens per request, 100,000 requests/month

$14.00

RAG pipeline

6,000 input / 700 output tokens per request, 30,000 requests/month

$24.30

Batch summarization

20,000 input / 1,500 output tokens per request, 5,000 requests/month

$12.25

Price history

Changes we have documented since we began tracking

No price changes recorded since we began tracking.

Llama 4 Scout pricing FAQ

How much does Llama 4 Scout cost per 1M tokens?
Llama 4 Scout costs $0.10 per 1M input tokens and $0.30 per 1M output tokens.
How much does Llama 4 Scout cost per request?
A typical request of 800 input and 200 output tokens costs about $0.00014 on Llama 4 Scout.
Is Llama 4 Scout cheaper than Llama 4 Maverick?
Llama 4 Scout is cheaper than Llama 4 Maverick on input tokens, by about 33%.
Does Llama 4 Scout have cache pricing?
No cache discount is documented for Llama 4 Scout on the provider's pricing page.