Skip to content
LLMs
Meta Llama logo

Meta: Llama 4 Maverick

by Meta Llama

Meta: Llama 4 Maverick is a large language model from Meta Llama. It costs $0.188 per million input tokens and $0.652 per million output tokens. Its context window is 524K tokens.

Tool callingStructured outputPrompt cachingOpen weightsimage input
Input / 1M tokens
$0.188
Output / 1M tokens
$0.652
Cached input / 1M
$0.050

On repeated prefixes

Context window
524K

tokens

Who serves it cheapest

3 hosts serve Llama 4 Maverick. Same weights, same API - the price difference is pure margin and routing.

Providers serving Meta: Llama 4 Maverick, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
DigitalOceanCheapest$0.188$0.652128K-100.0%
Parasailfp8$0.350$1.00524K-100.0%
Google$0.350$1.15524K--

The spread between DigitalOcean and Google is 1.8× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Coding index
16.3
Agentic index
0.6

About 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...

Specifications

Meta: Llama 4 Maverick specifications
Model IDmeta-llama/llama-4-maverick
ProviderMeta Llama
Context window524K tokens
Max output16K tokens
Input modalitiestext, image
Output modalitiestext
Knowledge cutoff2024-08-31
Open weightsYes - meta-llama/Llama-4-Maverick-17B-128E-Instruct
ReleasedApril 5, 2025

Cheaper alternatives

Models that cost less than Llama 4 Maverick while keeping at least half its context window and every input modality it supports.

Qwen3.6 35B A3B

$0.100 in · $0.900 out

about the same cheaper

MiniMax M3.1 Flash

$0.150 in · $0.600 out

1.2× cheaper

DeepSeek V4.1 Flash 1017

$0.150 in · $0.600 out

1.2× cheaper

Mistral Small 4

$0.150 in · $0.600 out

1.2× cheaper

Qwen3 VL 30B A3B Instruct

$0.150 in · $0.600 out

1.2× cheaper

Frequently asked

How much does Meta: Llama 4 Maverick cost?

$0.188 per million input tokens and $0.652 per million output tokens. Cached input reads cost $0.050 per million tokens.

What is the context window of Meta: Llama 4 Maverick?

524K tokens, with up to 16K tokens of output per request.

Which provider serves Meta: Llama 4 Maverick cheapest?

DigitalOcean at $0.188 per million input tokens - 1.8× cheaper than Google, the most expensive of the 3 hosts serving it.