Llama 4 Scout 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-scout
List price per million tokens
- Input
- $0.10
- Cached input
- n/a
- Output
- $0.30
- Context window
- 1.31M tokens
Note: Open-weight. OpenRouter headline; hosts range $0.08-$0.25 in / $0.24-$0.70 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.
| Task | Per 1,000 tries | Per 1,000 that work, 8 in 10 | Per 1,000 that work, 6 in 10 | Per 1,000 that work, 4 in 10 |
|---|---|---|---|---|
| Support bot answer3,000 in / 300 out | $0.39 | $0.49 | $0.65 | $0.97 |
| Invoice field extraction2,500 in / 250 out | $0.33 | $0.41 | $0.54 | $0.81 |
| Lead scoring1,200 in / 100 out | $0.15 | $0.19 | $0.25 | $0.37 |
| Email reply draft1,500 in / 400 out | $0.27 | $0.34 | $0.45 | $0.68 |
| Translation900 in / 800 out | $0.33 | $0.41 | $0.55 | $0.82 |
| Search re-ranking4,000 in / 50 out | $0.41 | $0.52 | $0.69 | $1.04 |
Work out your own real cost per resultTest Llama 4 Scout on your own prompt
Compare Llama 4 Scout with
- Llama 4 Maverick$0.35 in / $1.00 outSwitch cost
- Llama 3.3 70B Instruct$0.71 in / $0.71 outSwitch cost
- GPT-5 nano$0.05 in / $0.40 outSwitch cost
- Gemini 2.5 Flash-Lite$0.10 in / $0.40 outSwitch cost
- GPT-6 Luna$0.10 in / $0.50 outSwitch cost
Questions
How much does the Llama 4 Scout API cost?
$0.10 per million input tokens and $0.30 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 Scout?
A support bot answer (about 3,000 tokens in, 300 out) costs $0.00039 per try. If 6 in 10 work first time, each answer that works really costs $0.00065, because the redone ones were paid for too.