Llama 3.3 70B API Pricing
Short answer
Llama 3.3 70B costs $0.72 per 1M input tokens and $0.72 per 1M output tokens . Context window: 128K. Last verified 2026-06-17 from aws.amazon.com. Confidence: Auto.
Llama 3.3 70B is Meta's popular open-weight workhorse, hosted across many inference providers with a wide price spread.
Input
$0.72 /1M
Output
$0.72 /1M
Cached input
— /1M
Input pricing$0.72
Output pricing$0.72
Limits & capabilities
Context window128K
Max output—
Modalitytext input/output
ChannelAWS Bedrock
ProviderMeta
Best for
Open weightGeneralCheap
Open-weight; price ranges ~3-10x across hosts. Groq is fastest; OpenRouter routes to the cheapest.
Last checked Auto
More from Meta
Llama 4 Scout
$0.10 /1M in
$0.30 /1M out
Open weight, Ultra-long context, Multimodal
Llama 4 Maverick
$0.15 /1M in
$0.60 /1M out
Open weight, Reasoning, Multimodal