Metallama familyActive

Llama 4 Maverick 17B 128E Instruct

Open multimodal Llama model for strong reasoning and fast responses

JSONEmbed chartCompare
Context
524,288
Max output
8,192
Input / 1M
$0.35
Output / 1M
$1.15
Providers
1
01Profile

Profile

Released
2025-04-29
Last updated
2025-04-29
Knowledge cutoff
2024-08
Weights
Open
02Capabilities

Capabilities

Input
text · image
Output
text
Reasoning
No
Tool calling
Yes
Structured output
Yes
Attachments
Yes
Cache read
Cache write
03Pricing

Pricing across 1 providers

Per 1M tokens, USD. Sorted by input price. First-party row highlighted.

ProviderProvider model idInputOutputCache readContext
google-vertexmeta/llama-4-maverick-17b-128e-instruct-maas$0.35$1.15Not listed524,288
04History

Change history

1+ recent events since 2025-04-29

2026-02-15Addedgoogle-vertexoffering→ new
as of 2026-09-16
About ·Corrections ·Contact ·Privacy ·EN / 中文 / 繁體
HomeModelsLabsProvidersToolsRankingsChangesNews