How much does Llama 4 Maverick cost?

Llama 4 Maverick costs $0.20/M input tokens and $0.696/M output tokens.

What is the context length of Llama 4 Maverick?

Llama 4 Maverick has a 1,048,576 token context window.

Does Llama 4 Maverick support tool calling and structured outputs?

Yes. Llama 4 Maverick accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does Llama 4 Maverick support?

Llama 4 Maverick accepts text and images as input and returns text.

Which providers serve Llama 4 Maverick?

Llama 4 Maverick is served by 5 providers on OpenRouter: DigitalOcean, DeepInfra, NovitaAI, Parasail and Google Vertex. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Llama 4 Maverick released?

Llama 4 Maverick was released on 2025-04-05. Its knowledge cutoff is 2024-08-31.

Meta: Llama 4 Maverick

Name: Meta: Llama 4 Maverick
Author: meta-llama

meta-llama/llama-4-maverick

Model weights

Compare

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 pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.

Maverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.

Modalities

In / Out Price

$0.20 / $0.696per 1M

Context

Released

Apr 5, 2025

Knowledge Cutoff

Aug 2024

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

Latency / throughput


$0.20	$0.696	--	0.86s	7 tps	99.70%
$0.20	$0.80	--	0.33s	52 tps	99.77%
$0.27	$0.85	--	0.45s	51 tps	99.88%
$0.35	$1.00	$0.17	0.70s	66 tps	99.96%
$0.35	$1.15	--	0.85s	101 tps	99.94%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

101tok/s

P50, best across providers

Latency

0.33s

P50, best provider

Latency / throughput

AutoExacto Benchmarks

GPQA DiamondTAU-Bench

NovitaAI

64.9%--

DeepInfra

64.4%--

DigitalOcean

66.5%46.5%

auto-routing

66.6%43.9%

Parasail

65.0%44.4%

+1 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.99%

Availability over the last 3 days

Last 72 hours

Availability 99.99%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.99%

Without Routing

96.49%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Pocket Girl AI

new

1.53Btokens

Chatters Inner Circle

new

738Mtokens

RushChat

new

369Mtokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

368Mtokens

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

339Mtokens