@cf/meta/llama-4-scout-17b-16e-instruct vs llama-4-maverick
Lower price
@cf/meta/llama-4-scout-17b-16e-instruct
Faster
llama-4-maverick
Higher efficiency
@cf/meta/llama-4-scout-17b-16e-instruct
Input price
$0.00
$0.15
Output price
$0.00
$0.60
Context window
10000K
1049K
Throughput
118 tok/s
158 tok/s
Availability
98.5%
100.0%
Cost / task
$0.000
$0.001
Efficiency score
96
96
Estimated monthly cost by workload
Metric
-CF
LLAMA-4-MAVERI
Chat assistant
$0.00
$117.00
RAG / long context
$0.00
$234.00
Agent / tool use
$0.00
$324.00
Efficiency score: @cf/meta/llama-4-scout-17b-16e-instruct
Across price, speed and reliability, @cf/meta/llama-4-scout-17b-16e-instruct offers the stronger overall balance for most workloads — but the right pick depends on your exact mix of input, output and latency needs.
Figures are illustrative demo data, not financial advice.
Frequently asked questions
Is @cf/meta/llama-4-scout-17b-16e-instruct or llama-4-maverick cheaper?+
@cf/meta/llama-4-scout-17b-16e-instruct has the lower input price — $0.00 vs $0.15 per 1M tokens — so for most blended workloads it is the more cost-effective of the two. Figures are illustrative demo data.
Which should I choose, @cf/meta/llama-4-scout-17b-16e-instruct or llama-4-maverick?+
Across price, speed and reliability, @cf/meta/llama-4-scout-17b-16e-instruct offers the stronger overall balance for most workloads — but the right pick depends on your exact mix of input, output and latency needs.