Model comparison

Llama 4 Maverick vs Llama 4 Scout: pricing, context and features compared

Llama 4 Maverick costs $0.1875 per million input tokens and $0.6525 per million output tokens; Llama 4 Scout costs $0.10 and $0.30. Here is how they compare on specs, on what real workloads cost, and on which to pick for what, from prices updated daily.

Maverick and Scout are Meta’s two Llama 4 models. Scout is the smaller one; hosted versions differ in context window and price, which matters more than the model card when you buy from an API.

Llama 4 MaverickMeta

Input / 1M: $0.1875
Output / 1M: $0.6525
Context: 128,000
Max output: 16,384

Open weights: this is the price of OpenRouter’s top-ranked host, which may differ from Meta’s own API price.

Full Llama 4 Maverick pricing and specs

Llama 4 ScoutMeta

Input / 1M: $0.10
Output / 1M: $0.30
Context: 327,680
Max output: 16,384

Open weights: this is the price of OpenRouter’s top-ranked host, which may differ from Meta’s own API price.

Full Llama 4 Scout pricing and specs

Verdict

Llama 4 Maverick or Llama 4 Scout: which to pick

Llama 4 Scout has the lower list prices: 1.9× cheaper per input token and 2.2× per output token. On our data, Llama 4 Maverick has the edge for repeated prompts, and Llama 4 Scout for the lowest bill and very long prompts. For scale, a support chatbot handling 1,000 requests a day costs about $13.36 a month on Llama 4 Maverick and $8.21 on Llama 4 Scout.

Lowest bill for typical workloadsPick Llama 4 Scout: Llama 4 Scout costs less for the support chatbot, RAG app and document summariser (1.6× to 1.9× cheaper) and about the same for the coding agent.
Very long prompts (whole codebases, long documents)Pick Llama 4 Scout: Llama 4 Scout reads up to 327,680 tokens per request, against 128,000 for Llama 4 Maverick.
Long replies (reports, large code files)Either: Both cap a single reply at about 16,384 tokens.
Images, audio, video or files in the promptEither: Both accept images as well as text.
Repeated long prompts (prompt caching)Pick Llama 4 Maverick: Llama 4 Maverick bills cached input at $0.05 per 1M; Llama 4 Scout publishes no cached price, so repeated prefixes are billed in full.
Overnight batch jobsEither: Neither has a batch price in our data, so jobs that can wait cost the same as real-time requests.
Self-hosting or choosing your own hostEither: Both have open weights, so you can run either yourself or buy it from several hosts; prices here are typical hosted prices.

Criteria use only list prices, published limits and the features each provider declares. We don’t rank answer quality; test both models on your own prompts before you commit.

Specs

Llama 4 Maverick vs Llama 4 Scout side by side

Specs of Llama 4 Maverick and Llama 4 Scout; the better value on each row is marked
Spec	Llama 4 Maverick	Llama 4 Scout
Provider	Meta	Meta
Input / 1M tokens	$0.1875	$0.10 (better)
Output / 1M tokens	$0.6525	$0.30 (better)
Cached input / 1M	$0.05 (better)	Not published
Batch in / out	No batch price	No batch price
Long-prompt price	None	None
Context window	128,000	327,680 (better)
Max output	16,384	16,384
Accepts	text, images	text, images
Image input	Yes	Yes
Tool calling	Yes	Yes
Reasoning mode	No	No
Prompt caching	Yes (better)	No
Structured output	Yes	Yes
Open weights	Yes	Yes
Knowledge cutoff	2024-08-31	2024-08-31
First listed	2025-04-05	2025-04-05

Prices in US dollars per million tokens. Highlighted: the lower price or larger limit where the difference is over 5%. Features are as declared by each provider’s API; “First listed” is when our data source first listed the model. Long-prompt prices apply to the whole request once the prompt passes the threshold.

Costs

What Llama 4 Maverick and Llama 4 Scout cost for real workloads

Workload	Tokens in / out	Requests/day	Llama 4 Maverick / month	Llama 4 Scout / month	Cheaper
Support chatbotCalculator: Llama 4 Maverick · Llama 4 Scout	1,500 / 400	1,000	$13.3650% cached	$8.21	Llama 4 Scout (1.6×)
RAG appCalculator: Llama 4 Maverick · Llama 4 Scout	6,000 / 500	500	$19.5620% cached	$11.41	Llama 4 Scout (1.7×)
Coding agentCalculator: Llama 4 Maverick · Llama 4 Scout	40,000 / 2,000	200	$26.8080% cached	$27.98	About the same
Document summariserCalculator: Llama 4 Maverick · Llama 4 Scout	8,000 / 600	300	$17.26no batch price	$8.94no batch price	Llama 4 Scout (1.9×)

Each row uses the same token counts for both models and list prices (for an open-weight model, the top-ranked host’s price on OpenRouter), with caching and batch discounts only where the provider publishes them. A month is 365 ÷ 12 days. The support chatbot reads 50% of its prompt from the cache. The RAG app reads 20% of its prompt from the cache. The coding agent reads 80% of its prompt from the cache. The document summariser runs as a batch job where a batch price exists. Open either model in the LLM cost calculator to change any number.

Tokenizers

Are their per-token prices comparable?

Not exactly. Each model splits text into tokens its own way, so the same prompt can be a different number of tokens on Llama 4 Maverick and Llama 4 Scout, and the cheaper per-token price isn’t always the cheaper bill. Where a tokenizer isn’t public or measured we say so rather than guess.

Model	Tokenizer	Tokens per 1,000 words	Output per 1M words
Llama 4 Maverick	We haven’t measured Llama 4 Maverick’s tokenizer, so its count for a given text isn’t known here.
Llama 4 Scout	We haven’t measured Llama 4 Scout’s tokenizer, so its count for a given text isn’t known here.

English prose, measured on the Universal Declaration of Human Rights (2026-10-11) or taken from the provider’s published words-per-token figure. Code, JSON and other languages use more tokens per word. Count your own text in the token counter or convert with tokens to words.

FAQ

Llama 4 Maverick vs Llama 4 Scout questions

Is Llama 4 Maverick cheaper than Llama 4 Scout?

Llama 4 Maverick costs $0.1875 per million input tokens and $0.6525 per million output tokens; Llama 4 Scout costs $0.10 and $0.30. For a support chatbot handling 1,000 requests a day, that is about $13.36 a month on Llama 4 Maverick against $8.21 on Llama 4 Scout, so Llama 4 Scout is 1.6× cheaper there. Try your own numbers in the LLM cost calculator.

Which has the bigger context window, Llama 4 Maverick or Llama 4 Scout?

Llama 4 Scout has the larger context window. Llama 4 Maverick reads up to 128,000 tokens (roughly 96,000 English words) and writes up to 16,384 tokens per reply. Llama 4 Scout reads up to 327,680 tokens (roughly 245,760 English words) and writes up to 16,384 tokens per reply. The window is shared between your prompt and the reply. Word counts use a rough 0.75 words per token; real ratios depend on the tokenizer.

Is Llama 4 Maverick or Llama 4 Scout better for coding?

We don’t publish benchmark scores, so this page can’t say which writes better code. What we can show is cost: a coding agent re-sending 40,000 tokens of context (80% cached) and writing 2,000 tokens, 200 times a day, costs about $26.80 a month on Llama 4 Maverick and $27.98 on Llama 4 Scout. Both support tool calling. Test both on tasks from your own repository.

Can Llama 4 Maverick and Llama 4 Scout read images?

Llama 4 Maverick accepts images as well as text. Llama 4 Scout accepts images as well as text. So both can read screenshots, photos and scanned pages. This is what each provider declares for its API, not a measure of how well it works.

Are Llama 4 Maverick and Llama 4 Scout open source?

Both have open weights: you can download them, run them on your own hardware, or buy them from several hosting providers. The prices on this page are typical hosted prices, so shop around. Check each model’s licence for commercial use, and see the VRAM calculator for the hardware a model needs.

Do Llama 4 Maverick and Llama 4 Scout count tokens the same way?

Not necessarily. Each model splits text into tokens with its own tokenizer, so the same prompt can be a different number of tokens on each, and per-token prices aren’t directly comparable. We haven’t measured Llama 4 Maverick’s tokenizer, so its count for a given text isn’t known here. We haven’t measured Llama 4 Scout’s tokenizer, so its count for a given text isn’t known here. Count your own text with the token counter or convert with tokens to words.

Explore

Go further

Guides

Compare