Skip to content
Toolsummary LLM price ledger

Meta Llama 3.1.8 B Instruct pricing

Source: litellm · updated 2026-11-16

Short answer: Meta Llama 3.1.8 B Instruct costs $0.020 per million input tokens and $0.060 per million output tokens. That is a 3:1 blended rate of $0.030 per million tokens, ranking it #28 of 822 tracked models by input price.
Input / 1M
$0.020
Output / 1M
$0.060
Output ÷ input
3.00×
Context window
128,000

Price breakdown

MetricUSD
Input, per 1M tokens$0.020
Output, per 1M tokens$0.060
Output ÷ input multiple3.00×
3:1 blended, per 1M tokens$0.030
Context window128,000 tokens
Vendornebius

What a typical workload costs

Monthly volumeInput costOutput costTotal
1M in / 250K out$0.020$0.015$0.035
10M in / 2.5M out$0.200$0.150$0.350
100M in / 25M out$2.00$1.50$3.50

Other nebius models

ModelInputOutput
Qwen 2.5 Coder 7 B$0.010$0.030
Llama Guard 3.8 B$0.020$0.060
Qwen 2 VL 7 B Instruct$0.020$0.060
Mistral Nemo Instruct 2407$0.040$0.120
Qwen 2.5 32 B Instruct$0.060$0.200

Compare against

Cheaper alternatives

Next cheaper option: Mistral Nemo at $0.029 per 1M input tokens. Next step up: Ling 3.0 Flash at $0.021 per 1M input tokens.


Spotted a price that is out of date? Submit a correction.