Llama 4 Maverick

Provider: Meta Llama US

Input price
$0.35
/ 1M tokens
Output price
$1.00
/ 1M tokens
Cache price
$0.17
/ 1M tokens (read)
Context
524K tokens
Max output 33K tokens

Overview

Meta's Llama 4 Maverick is a multimodal reasoning and specialist model utilizing a 17-billion active parameter mixture-of-experts architecture.

Strengths

  • 524288 token context window supports large documents
  • Native vision and function-calling capabilities included
  • Cached input drops cost to $0.17 per million tokens

Best use cases

  • Multimodal document analysis tasks
  • Complex structured JSON data extraction

Pricing position

Input at $0.35 matches Mistral Small 3.1, but the $1.00 output is double Qwen2.5 72B.

Caveats

No free tier available across any hosting providers.

Notes drafted by an LLM from the figures on this page (2026-11-12) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
33K tokens
Knowledge cutoff
2024-08-31
Listed on OpenRouter
2025-04-05
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Image inputFunction callingJSON output

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.08
1M (small app) 1 0.5 $0.85
10M (mid scale) 10 5 $8.50
100M (large) 100 50 $85.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Meta Llama

Similar-priced models

Source: OpenRouter API (meta-llama/llama-4-maverick)