Sign inGet started
Model · OpenRouter

Meta Llama/Llama 4 Maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

Author / organizationMeta Llama
AccessHosted API (no weights listed here)
Price per million tokens$0.1875 in · $0.6525 out
Context window524,288 tokens
Taskimage-text-to-text
Created5 April 2025
Last updated at source—
image-text-to-texthostedtool-use
Embed this entry
<iframe src="https://silytics.si/embed/item/c622b14d-cdfc-422e-821f-2f2c5007f681" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Popularity, last 6 days

0 now. Counts as reported by the source, snapshotted daily by Silytics.

Price and speed history

USD per million tokens

00.30.50.8110-1510-1610-1710-1810-1910-20Input · 10-15: 0.188Input · 10-16: 0.188Input · 10-17: 0.188Input · 10-18: 0.188Input · 10-19: 0.188Input · 10-20: 0.188Output · 10-15: 0.653Output · 10-16: 0.653Output · 10-17: 0.653Output · 10-18: 0.653Output · 10-19: 0.653Output · 10-20: 0.653
InputOutput

More from Meta Llama

Silytics shows public metadata from OpenRouter and links to the original. Information may be incomplete or out of date. Last refreshed 20 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.