Llama 4 Scout
Efficient
Long-context Llama 4 with a 512K window, the open-weights answer to long-document workloads.
Llama 4 Scout is a efficient AI model from Meta. It costs $0.100 per million input tokens and $0.350 per million output tokens (blended $0.175/M), with a 512,000-token context window.
INPUT
$0.100/M
per million input tokens
OUTPUT
$0.350/M
per million output tokens
BLENDED 70/30
$0.175/M
0.0%over 80 days · hover to read
CONTEXT
512,000
tokens
What it is good at
- 512K context
- Open weights
- MoE efficiency
Typical use cases
- Long document Q&A
- Codebase analysis
- Self-hosted long context
Benchmarks
vs. best public score
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.
More from Meta
See all 20 →Muse Spark 1.2
Frontier · 1,049,000 ctx
in $1.250/Mout $4.250/M
Llama 4 Maverick
Frontier · 128,000 ctx
in $0.200/Mout $0.600/M
Llama 3.3 70B
Open · 128,000 ctx
in $0.230/Mout $0.400/M
Llama 3.1 405B
Large · 128,000 ctx
in $0.800/Mout $0.800/M
Llama 3.1 70B
Balanced · 128,000 ctx
in $0.350/Mout $0.400/M
Llama 3.1 8B
Compact · 128,000 ctx
in $0.100/Mout $0.100/M
Frequently asked questions
How much does Llama 4 Scout cost?
Llama 4 Scout costs $0.100 per million input tokens and $0.350 per million output tokens, for a blended reference rate of $0.175 per million tokens.
What is Llama 4 Scout's context window?
Llama 4 Scout supports up to 512,000 tokens of context in a single request.
What is Llama 4 Scout best for?
Llama 4 Scout is well suited to 512K context, Open weights and MoE efficiency.
Who makes Llama 4 Scout?
Llama 4 Scout is developed and served by Meta.