Llama 4 Maverick vs Llama 4 Scout: API Price & Benchmark Comparison (INR)
Side-by-side pricing
| Llama 4 Maverick | Llama 4 Scout | |
|---|---|---|
| Input price / 1M tokens | ₹20.63 | ₹10.32 |
| Output price / 1M tokens | ₹82.53 | ₹30.95 |
| Context window | 1,048,576 | 1,310,720 |
| Provider | Meta | Meta |
Velona effective INR prices, refreshed every 6 hours (last: 2026-07-28T17:32:59Z).
When to pick which
Scout is slightly cheaper ($0.10/$0.30 vs $0.15/$0.60 per million) and its headline feature is a 10M-token context window, ten times Maverick's already-large 1M. Maverick is the more capable model per token: more active experts, better reasoning, coding, and multimodal quality. Choose Scout when the problem is fitting things in: entire codebases, book-length document sets, or months of chat history in one call. Choose Maverick when answer quality matters more than raw capacity. For most production chat and agent workloads, Maverick is the better default despite the small premium.
Benchmarks
Llama 4 Maverick
Benchmarks
Independent scores from Artificial Analysis.
Llama 4 Scout
Benchmarks
Independent scores from Artificial Analysis.
Cost calculator for both models
Frequently asked questions
Which is cheaper: Llama 4 Maverick or Llama 4 Scout?
On input tokens, Llama 4 Maverick costs ₹20.63/1M and Llama 4 Scout costs ₹10.32/1M through Velona. Output tokens: ₹82.53 vs ₹30.95 per 1M.
Can I switch between Llama 4 Maverick and Llama 4 Scout without changing code?
Yes. Both are behind Velona's single gateway API. Change the model id in your request body and everything else stays the same, including your INR wallet.
Are these prices current?
Prices are regenerated every 6 hours from live provider pricing and the current USD→INR rate, so the figures on this page track what you'd actually be billed.
Velona is India's INR-native AI API gateway with 300+ models behind one API key, UPI top-up from ₹10, no foreign card needed.