Llama 4 Maverick
language modelMeta
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...
Key facts
| Made by | Meta |
|---|---|
| Type | language model |
| Released | April 5, 2025 |
| Reads at once | 524,288 tokens |
| Price (API, per million tokens) | $0.19 in · $0.65 out |
| Input → output | text, image → text |
Questions about Llama 4 Maverick
Who makes Llama 4 Maverick?
Llama 4 Maverick is made by Meta.
When was Llama 4 Maverick released?
We first saw Llama 4 Maverick listed on April 5, 2025.
How much does Llama 4 Maverick cost?
Through OpenRouter it costs $0.19 per million input tokens and $0.65 per million output tokens. Prices change, so check the provider before you build on it.
How much text can Llama 4 Maverick read at once?
Up to 524,288 tokens, roughly 393.2K words.
More from Meta
optMeta · language model
May 11, 2022released
Llama 3.2Meta · language model
Sep 18, 2024released
Musicgen-MediumMeta · voice and audio model
Jun 8, 2023released
Wav2vec2-960hMeta · voice and audio model
Mar 2, 2022released
Meta-Llama-3Meta · language model
Apr 17, 2024released
Seamless-M4t-V2-LargeMeta · voice and audio model
Nov 29, 2023released
Other language models
gpt2Openai Community · language model
Mar 2, 2022released
Qwen3.8Alibaba (Qwen) · language model
Aug 5, 2026released
Qwen3 VLAlibaba (Qwen) · language model
Sep 23, 2025released
Qwen2.5 VLAlibaba (Qwen) · language model
Jan 26, 2025released
optMeta · language model
May 11, 2022released
Qwen3.6Alibaba (Qwen) · language model
Apr 15, 2026released
Ollamaollama · language model
Jun 26, 2023released
pythiaEleutherAI · language model
Feb 8, 2023released
Modelcast collects this page automatically from public sources (OpenRouter). Facts are copied from those sources, not written by the maker. Not affiliated with Meta.