← All models
L
Llama 4 Scout
Meta
Meta's latest efficient model with a massive 10M token context window at extremely low cost
Input price$0.17 / 1M tokens
Output price$0.17 / 1M tokens
Context window10M tokens
Last updated2026-04-22
Quick calculator
Per request
$0.000255
Daily
$2.55
Monthly
$76.50
per month · 30-day estimate
Yearly
$930.75
Tips to reduce cost
- →Use prompt caching to reuse repeated system prompts
- →Trim whitespace and reduce verbose instructions
- →Use a smaller model for classification or routing tasks
- →Batch async requests to get 50% discount (OpenAI/Anthropic)
- →Cache identical requests at the application layer
Similar models from Meta
Compared at your current token settings
About Llama 4 Scout
Llama 4 Scout is a budget large language model from meta, priced at $0.17/1M input tokens and $0.17/1M output tokens. It is 94% cheaper than the market average and best suited for huge context at low cost. The 10M context window makes it suitable for very long documents, large codebases, and book-length inputs.
For most production workloads, the cost breakdown is dominated by input tokens (system prompts, context, retrieved documents) rather than output. At this price point, Llama 4 Scout is one of the most cost-effective options for high-volume tasks.
Frequently Asked Questions
How much does Llama 4 Scout cost per 1,000 tokens?
Llama 4 Scout costs $0.0002 per 1,000 input tokens and $0.0002 per 1,000 output tokens.
What is Llama 4 Scout's context window?
Llama 4 Scout supports a context window of 10M tokens, which is suitable for very long documents, large codebases, and extended multi-turn conversations.
How does Llama 4 Scout compare to GPT-4o on price?
Llama 4 Scout is 94% cheaper than the market average on input tokens. At $0.17/1M input vs $2.50/1M for GPT-4o, the cost difference becomes significant at scale — 10,000 requests/day with 1,000 input tokens each costs $51/month with Llama 4 Scout vs $750/month with GPT-4o.