Meta
Frontier

Llama 4 Maverick

Frontier

The flagship Llama 4, an MoE-architecture model designed for cheap, high-throughput inference across the open-weights ecosystem.

Llama 4 Maverick is a frontier AI model from Meta. It costs $0.3500 per million input tokens and $1.00 per million output tokens (blended $0.5450/M), with a 128,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.3500/M
per million input tokens
OUTPUT
$1.00/M
per million output tokens
BLENDED 70/30
$0.5450/M

+66.7%over 64 days · hover to read

Llama 4 Maverick — blended price

Reconstructed from 64 days of recorded rate-card changes. Prices hold flat between changes because that is what a posted price does — no value here is interpolated.

CONTEXT
128,000
tokens

From OpenRouter's listing, read on 17 Nov 2026.

What it is good at
  • MoE for cheap inference
  • Open weights
  • Wide hosted availability
  • Multimodal
Typical use cases
  • Self-hosted general chat
  • Multi-cloud deployments
  • Fine-tune base

Benchmarks

vs. best public score
MMLU85.5%
Multitask academic knowledge across 57 subjects. Source: Meta (self-reported), MMLU (5-shot), pre-trained model, read 2026-11-10.
Graduate-level science questions, "Google-proof". Source: Meta (self-reported), GPQA Diamond (0-shot), read 2026-11-10.
MATH61.2%
High-school competition math problems. Source: Meta (self-reported), MATH (4-shot, em_maj1@1), pre-trained model, read 2026-11-10.
LMArena Elo1327 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Meta

See all 20 →

Price history

4 recorded changes
Recorded price changes for Llama 4 Maverick, newest first
DateRateWasNowChange
8 Nov 2026Input$0.1875$0.3500+87%
8 Nov 2026Output$0.6525$1.00+53%
15 Sept 2026Output$0.6000$0.6525+8.8%
15 Sept 2026Input$0.1500$0.1875+25%

Rates per million tokens, as published by the provider or its router listing. Tracking runs since 3 May; anything earlier is not on record. See every tracked price change.

Frequently asked questions

How much does Llama 4 Maverick cost?

Llama 4 Maverick costs $0.3500 per million input tokens and $1.00 per million output tokens, for a blended reference rate of $0.5450 per million tokens.

What is Llama 4 Maverick's context window?

Llama 4 Maverick supports up to 128,000 tokens of context in a single request.

What is Llama 4 Maverick best for?

Llama 4 Maverick is well suited to MoE for cheap inference, Open weights and Wide hosted availability.

Who makes Llama 4 Maverick?

Llama 4 Maverick is developed and served by Meta.

Compared with

Terms used on this page