Meta (Llama API)

Llama API: Llama 4 Maverick

Meta's first-party hosted Llama API. Sample entry.

USD per 1M output tokens

$0.85

Unverified sample

#5 cheapest of 25 in Large language models

Capabilities, explained

What this API can do, and what each capability means for your project.

Input price

$0.27

Cost of the text, images and files you send to the model.

Context window

1,000K tokens

How much text the model can read at once. 200K tokens ≈ a 500-page book.

Max output

—

Longest single response the model can write.

Input types

text, image

What kinds of input the model understands besides text.

Tool use / function calling

Yes

The model can request calls to your functions/APIs with structured arguments, the basis of agents.

Guaranteed JSON output

—

The API can force the response to match a JSON schema you provide.

Extended reasoning

—

The model can 'think' step by step before answering, improving hard math/coding at extra cost and latency.

Open weights

Yes

The model weights are downloadable, so you can self-host it or switch hosting providers without changing models.

Typical latency

—

How long until the first useful output arrives. Lower is better for interactive apps; batch jobs rarely care.

Only one price recorded so far. The chart appears once the price changes.