Llama 4 Maverick

meta-llama/llama-4-maverick

by Meta·Text + Image·1048K context·Released 2025-04-05·Llama 4 Community

open-weightlong-contextvision

Overview

Meta's open-weight Llama 4 Maverick, a 400B-parameter sparse MoE (17B active) with a very large context window and native image understanding. Strong general reasoning and multilingual coverage, hosted by a wide range of providers so live prices stay competitive. A solid open option when you want frontier-ish breadth without first-party-only pricing, though it's heavier and pricier per token than the small open models.

Benchmarks

Standardized scores (0–100), normalized across the catalog.

Intelligence70

Coding74

Instruction following86

Providers

LLMRouteHub routes to the cheapest healthy provider by default. Showing the top 5 of 9 providers by routed volume.

Provider	Input	Output	Throughput	Uptime
Lambda	$0.22	$0.94	102 tok/s	99.6%
Hyperbolic	$0.24	$1.00	95 tok/s	99.4%
Parasail	$0.28	$1.20	88 tok/s	99.3%
DeepInfra	$0.33	$1.39	81 tok/s	99.1%
Together	$0.34	$1.46	73 tok/s	99%

Use this model

curl https://llmroutehub.com/api/v1/chat/completions \
  -H "Authorization: Bearer $LLMROUTEHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-4-maverick",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'