Meta

Llama 4 Maverick

Meta's Llama 4 Maverick MoE (17B active / ~400B total, 128 experts) for multilingual multimodal workloads, on Together AI, AWS Bedrock, and Azure.

ActiveReleased April 1, 2025Knowledge cutoff August 1, 2024Available from 11 providers
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data (vendor fine-tune API or self-hosted open weights).

Source: Llama 4 Scout on Together AI, Llama 4 Maverick on Together AI, Llama 4 Scout on Hugging Face, AWS Bedrock Llama pricing

Price per 1M tokens
$0.27 in / $0.35 out
Context window1,048,576
Max output16,384
ModalitiesText, Image → Text
Priced across11 providers

Specs

Details that do not fit the rate card above.

Architecture128-expert MoE; 17B active / ~400B total

Pricing

Every billing leg from the live catalog, in USD per 1M tokens.

Billing legRate
Input$0.27 / M
Output$0.35 / M

Cost calculator

Billing-grade math over the rate card above, including the thinking tokens most estimates miss.

Estimated monthly cost
$61.00
at current list prices
Fresh input$54.00
Output$7.00
Track this automatically →

Compare providers

The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.

PlatformInput / MOutput / MCache read / MBatchAccess
Together AILowest
$0.27$0.35——Direct
DigitalOcean
$0.2$0.696——via OpenRouter
DeepInfra
$0.2$0.8——via OpenRouter
Novita
$0.27$0.85——via OpenRouter
AWS Bedrock
$0.24$0.97—✓Direct
AWS Bedrock · Regional
from$0.24$0.97—✓Direct
Azure AI Foundry
$0.25$1——Direct
Parasail
$0.35$1$0.17—via OpenRouter
Azure AI Foundry · Data zone
$0.275$1.1——Direct
Azure AI Foundry · Regional
from$0.275$1.1——Direct
Google
$0.35$1.15——via OpenRouter

Regional deployments are priced per region; the lowest available region rate is shown.

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $0.27 / $0.35 per 1M since May 6, 2026.

More from Meta

Other models from the same provider.

Muse Spark 1.1
meta/muse-spark-1.1
$1.25 / $4.25 in / out per 1M
Llama 4 Scout
meta/llama-4-scout
$0.18 / $0.59 in / out per 1M
Llama 3.3 70B
meta/llama-3.3-70b
$1.04 / $1.04 in / out per 1M

Stop estimating. Track it.

SuperPenguin meters every Llama 4 Maverick call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.

Get started free

Rates are generated from SuperPenguin's live pricing catalog.