Benchmarks

Meta: Llama 4 Maverick

meta-llama/llama-4-maverick

Llama 4 Maverick is an open-weight model from Meta, ranking #154 of 235 on the TryAii Score. Its best showing is #6 on LiveBench. It's served by 5 independent hosts from $0.2/$0.696 per million input/output tokens — about half of what models at its level usually charge.

Prompt $/1M
$0.200
Completion $/1M
$0.696
Context
1,048,576 tok
Best provider
85 tok/s · Artificial Analysis

Specs

Model id
meta-llama/llama-4-maverick
Display name
Meta: Llama 4 Maverick
Modality
text+image->text
Tokenizer
Llama4
Instruct type
Context length
1,048,576
Max completion
115,200
Prompt $/1M
$0.200
Completion $/1M
$0.696
Free tier
no

Capabilities

  • Function callingno
  • JSON modeno
  • System promptno
  • Visionyes
  • Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Providertok/s
Artificial Analysis85
Googlefastest54
Parasail29
DeepInfra26
Novita24
SambaNova21
DigitalOcean10
meta-llamafastest