Llama 4 Maverick
Meta's multimodal MoE open model — 400k context, strong vision, designed for GPU cluster deployments.
Pricing
InputOpen weights
OutputSelf-hosted cost profile
Cost bandFree/open
Free tierOpen weights (Meta Llama license).
Limits
Context window1M checked Jul 19, 2026
Max outputRuntime-dependent
Knowledge cutoffSee release materials
DeploymentSelf-hosted, Hugging Face, Together, Groq
OpenAI-compatible APIYes
ModalitiesText, Image input
Where it fits
Best forLarge-scale self-hosted multimodal pipelines and research teams with H100 clusters.
Business fitThe most capable Meta open model when you have the hardware to run it.
Capabilities
Open weightsMoEMultimodalLong context
Benchmark scores
Composite80 / 100
Coding78 / 100 (LiveCodeBench)
Reasoning80 / 100 (MMLU-Pro)
Long context88 / 100 (RULER 400K)
Vision76 / 100 (MMMU)
Instruction following80 / 100 (IFEval)
Editorial aggregate of published benchmark results as of May 1, 2025. These are not independent measurements run by this site.
Change history
- Jul 19, 2026Context increaseLlama 4 Maverick context window now 1M
400kto 1M OpenRouter directory
Data
Last checkedJul 19, 2026
Cross-checked againstopenrouter.ai/meta-llama/llama-4-maverick
Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.