// pricing · September 2026

Meta (meta-llama) API Pricing

Every Meta (meta-llama) model's list price per 1M tokens — input, output and cached input — with context windows, LiveBench scores and what a real workload costs per month.

OpenRouter · refreshed every 15 minutesAll providers Best value models Cheapest with tool calling

8 Meta (meta-llama) models are listed, with a median list price of $0.100 per 1M input tokens and $0.310 per 1M output tokens. Paid prices run from $0.057 (Llama 3.1 8B Instruct) to $0.400 (Llama 3.1 70B Instruct) per 1M tokens blended.

Models: 8
Median input / 1M: $0.100; paid models
Median output / 1M: $0.310; paid models
Cheapest paid: $0.057; Llama 3.1 8B Instruct
Prompt caching: 1; publish a cached-input price

Meta (meta-llama) model prices

List prices in USD per 1M tokens. “Blended” is a 3:1 input:output mix; the per-month column prices the selected workload using each model's cached-input rate where it publishes one.

Showing 8 of 8 models · per-month column: 8K in / 600 out × 100K requests, 50% of input cached

LLM API list prices per 1M tokens, context windows and monthly workload cost

Llama 3.1 8B Instruct meta-llama/llama-3.1-8b-instruct	$0.050	$0.080	$0.025	$0.057	131K	—	$34.80
Llama 3.2 1B Instruct meta-llama/llama-3.2-1b-instruct	$0.027	$0.201	—	$0.071	60K	—	$33.66
Llama 3.2 3B Instruct meta-llama/llama-3.2-3b-instruct	$0.050	$0.330	—	$0.120	131K	—	$59.80
Llama 4 Scout meta-llama/llama-4-scout	$0.100	$0.300	—	$0.150	1.3M	—	$98.00
Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct	$0.100	$0.320	—	$0.155	131K	—	$99.20
Llama Guard 4 12B meta-llama/llama-guard-4-12b	$0.180	$0.180	—	$0.180	164K	—	$154.80
Llama 4 Maverick meta-llama/llama-4-maverick	$0.188	$0.652	—	$0.304	1.0M	—	$189.15
Llama 3.1 70B Instruct meta-llama/llama-3.1-70b-instruct	$0.400	$0.400	—	$0.400	131K	—	$344.00

Price your own workload

Meta (meta-llama) pricing FAQ

What is the cheapest Meta (meta-llama) model?

Llama 3.1 8B Instruct is the cheapest paid Meta (meta-llama) model, at $0.050 per 1M input tokens and $0.080 per 1M output tokens.

Why do output tokens cost more than input tokens?

Generating a token takes a full forward pass per token, while input is processed in parallel. Across the paid Meta (meta-llama) models listed here the median output price is $0.310 per 1M against $0.100 for input — reasoning tokens bill as output too.

Which Meta (meta-llama) models support prompt caching?

1 of 8 publish a separate cached-input price, which bills repeated prompt prefixes at a fraction of the normal input rate. Filter the table by "Caching" to see them.

How current are these prices?

List prices are pulled from OpenRouter’s public models API and refreshed every 15 minutes. Batch discounts and enterprise pricing are not included.

What these prices include

List prices from OpenRouter's public models API, which mirrors provider pricing. Batch discounts and negotiated enterprise rates are not included.
Variants — :free and :batch listings are folded into their base model; its model page lists them.
Per-month cost is a floor: tokens you describe times list price. Cache writes and reasoning-token volume depend on your workload.