Skip to content

Llama 4 Maverick

MetaOpen weightsNon-reasoningVerifiedReleased Apr 5, 2025Input: text, image
Overall score
21.6
Rank 209 of 222 · 16.9–26.2
Context window
1M
1,000,000 tokens
Price per 1M tokens
$0.19 in · $0.65 out
Source: OpenRouter
Blended price
$0.30
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Reasoning59.3
  2. 2Multimodal56.0
  3. 3Instruction following#9350.3
  4. 4Knowledge47.6
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (2)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Agentic & tool use

MazeBench0#20 of 42

Multimodal

Design Arena Website871#88 of 91

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price (OpenRouter)$0.19$0.65—
OpenRouter meta-llama/llama-4-maverick$0.19$0.65$0.050

Self-hosted cost varies

Open weights

From the Hugging Face repository.

Parameters
402B
Licence
other
Downloads (30 days)
9.9K

Speed

Measured by us through OpenRouter (median of trials).

Not measured yet.

Related models

Similar score