Meta: 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 forw

Context
524K
Max output
16K
Input price
$0.19/1M tokens
Output price
$0.65/1M tokens

Capabilities

Reasoning & Interaction
Tool Calling
Output Control
Structured Output
JSON Mode

Details

Model IDmeta-llama/llama-4-maverick
Provider OpenRouter
Creator meta-llama
Familyllama-4
License—
Status—
Typechat
Input modalitiestext, image
Output modalitiestext
Open weight—
Parameters—
Architecture—
Context window524K tokens
Max input—
Max output16K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.19
Output
$0.65
Cache write
—
Cache read
$0.05
Batch in
—
Batch out
—

Family Comparison: llama-4

ModelContextMax outPricing
Meta: Llama 4 Scout1.3M16K$0.1$0.3
Meta: Llama 4 Maverick524K16K$0.19$0.65

API

GET/v1/models/openrouter/meta-llama/llama-4-maverick

Meta: Llama 4 Maverick

meta-llama/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 forw

Changes · 14 entries
meta-llama/llama-4-maverickupdateca7a400Nov 2, 2026, 03:02 AM
context_window1048576→524288
pricinginput$0.15→$0.188output$0.6→$0.653cached input$0.05
meta-llama/llama-4-maverickupdate42a9895Oct 20, 2026, 06:39 AM
context_window1048576→524288
meta-llama/llama-4-maverickupdateb61df6aOct 7, 2026, 06:39 AM
pricingcached input$0.05
meta-llama/llama-4-maverickupdatef13f134Sep 22, 2026, 06:39 AM
pricinginput$0.2→$0.188output$0.8→$0.653
meta-llama/llama-4-maverickupdateaf38e5cSep 21, 2026, 06:49 AM
pricinginput$0.188→$0.2output$0.653→$0.8
meta-llama/llama-4-maverickupdatea6d63d7Sep 15, 2026, 06:39 AM
max_output_tokens115200→16384
pricinginput$0.2→$0.188output$0.696→$0.653
meta-llama/llama-4-maverickupdatee3fc6e0Aug 31, 2026, 07:31 AM
max_output_tokens16384→115200
pricingoutput$0.8→$0.696
meta-llama/llama-4-maverickupdatebe35184Aug 17, 2026, 04:02 AM
pricingoutput$0.696→$0.8
meta-llama/llama-4-maverickupdate3cddff5Aug 13, 2026, 02:54 AM
pricingoutput$0.8→$0.696
meta-llama/llama-4-maverickupdate20c73acJul 17, 2026, 02:34 AM
pricinginput$0.15→$0.2output$0.6→$0.8
meta-llama/llama-4-maverickupdate82e6976Apr 7, 2026, 02:37 PM
descriptionLlama 4 Maverick 17B Instruct (128E) is a high-capacity m...→Llama 4 Maverick 17B Instruct (128E) is a high-capacity m...
meta-llama/llama-4-maverickupdate1cd659eMar 24, 2026, 04:19 AM
capabilitiesjson modeyes
meta-llama/llama-4-maverickupdate2b100acMar 23, 2026, 05:30 AM
model_typechat
release_date2025-04-05
taglineLlama 4 Maverick 17B Instruct (128E) is a high-capacity m...
tools["function_calling"]
meta-llama/llama-4-maverickcreate7f5c66fMar 21, 2026, 05:16 AM