Skip to content

Llama 4 Maverick API price, and what each result really costs

Meta, listed 5 Apr 2025. Price checked 12 Nov 2026; unchanged since we started tracking it. Source: OpenRouter. meta-llama/llama-4-maverick

List price per million tokens

Input
$0.35
Cached input
n/a
Output
$1.00
Context window
524K tokens

Note: Open-weight; no first-party list price. OpenRouter headline; hosts range $0.19-$0.35 in / $0.65-$1.15 out.

What it costs per task, and per task that works

Six common task shapes with typical token counts. The real cost counts the tries that get redone; the rates are examples, not measurements.

TaskPer 1,000 triesPer 1,000 that work, 8 in 10Per 1,000 that work, 6 in 10Per 1,000 that work, 4 in 10
Support bot answer3,000 in / 300 out$1.35$1.69$2.25$3.38
Invoice field extraction2,500 in / 250 out$1.13$1.41$1.88$2.81
Lead scoring1,200 in / 100 out$0.52$0.65$0.87$1.30
Email reply draft1,500 in / 400 out$0.93$1.16$1.54$2.31
Translation900 in / 800 out$1.12$1.39$1.86$2.79
Search re-ranking4,000 in / 50 out$1.45$1.81$2.42$3.62

Work out your own real cost per resultTest Llama 4 Maverick on your own prompt

Compare Llama 4 Maverick with

Worked-through switches: GPT-4o → Llama 4 Maverick: cost and quality on real tasks

Questions

How much does the Llama 4 Maverick API cost?

$0.35 per million input tokens and $1.00 per million output tokens. Price checked 12 Nov 2026; unchanged since we started tracking it.

What does a result that works really cost with Llama 4 Maverick?

A support bot answer (about 3,000 tokens in, 300 out) costs $0.0014 per try. If 6 in 10 work first time, each answer that works really costs $0.0023, because the redone ones were paid for too.