10,000 Llama 3.2 3B Instruct tokens cost $0.0003 as input or $0.0005 as output. Most workloads land in between — a 70/30 input/output split costs about $0.00036. Verified Aug 19, 2026
Interactive calculator
10,000 in · 0 out
Input price
$0.03 / 1M tokens
Output price
$0.05 / 1M tokens
Uncached pricing. Add caching and monthly projections in the full calculator.
What 10,000 tokens buys in practice
$0.00034
80% input / 20% output — short replies over conversation history.
$0.00032
90% input / 10% output — long retrieved context, grounded answers.
$0.00031
95% input / 5% output — full documents in, structured extraction out.
Same 10,000 tokens on other models
Related calculations
FAQ
10,000 input tokens cost $0.0003; 10,000 output tokens cost $0.0005. A typical 70/30 input/output mix costs about $0.00036. Rates: $0.03/M input, $0.05/M output.
A chat-style request of ~4,800 tokens (4,000 in + 800 out) means 10,000 tokens is roughly 2.1 requests. For a RAG workload with ~8,500 tokens per request, about 1.2 requests.
Llama 3.2 3B Instruct has no published cached-input discount on its official pricing page; all input is billed at $0.03/M.