Llama 4 Maverick
Open weightVisionToolsMeta · Released April 2025 · Knowledge cutoff August 2024
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...
It belongs to Meta's open-weight Llama family: Llama 4 Maverick is the capability lead, Scout the efficient long-context sibling, and the 3.x line remains a dependable workhorse.
Facts and pricing
- Provider
- Meta
- Context window
- 1.0M tokens
- Input price
- 1.7 credits / 1M tokens ($0.15 raw)
- Output price
- 6.6 credits / 1M tokens ($0.60 raw)
- Vision (image input)
- Yes
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.
Try Llama 4 Maverick now
What Llama 4 Maverick is best for
- Everyday chat and drafting on an open-weight model with transparent lineage
- Very long documents and codebases: a 1.0M-token window fits entire books or repositories in one conversation
- Working with images: screenshots, charts, photos and scanned documents alongside text
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a open weight model like Llama 4 Maverick:
- Draft a project update from these rough notes
- Explain how HTTPS works to a curious teenager
- Turn this list of features into a changelog entry
- Brainstorm objections to this proposal and how to answer them
Meta family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Llama Guard 4 12B | 164K | 2.0 | 2.0 | April 2025 |
| Llama 4 Maverick | 1.0M | 1.7 | 6.6 | April 2025 |
| Llama 4 Scout | 10M | 1.1 | 3.3 | April 2025 |
| Llama 3.3 70B Instruct (free) | 131K | 0 | 0 | December 2024 |
| Llama 3.3 70B Instruct | 131K | 1.1 | 3.5 | December 2024 |
| Llama 3.2 1B Instruct | 131K | 0.30 | 2.2 | September 2024 |
| Llama 3.2 11B Vision Instruct | 131K | 3.8 | 3.8 | September 2024 |
| Llama 3.2 3B Instruct (free) | 131K | 0 | 0 | September 2024 |
| Llama 3.2 3B Instruct | 131K | 0.55 | 3.6 | September 2024 |
| Llama 3.1 8B Instruct | 131K | 0.22 | 0.33 | July 2024 |
Compare Llama 4 Maverick
- Llama 4 Maverick vs DeepSeek V4 Pro
- Llama 4 Maverick vs Qwen3.7 Max
- Llama 4 Maverick vs Mistral Medium 3.5
- Llama 4 Maverick vs Llama 4 Scout
- Llama 4 Maverick vs Llama 3.3 70B Instruct
Frequently asked questions
- What is Llama 4 Maverick?
- Llama 4 Maverick is an AI model by Meta. 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...
- How much does Llama 4 Maverick cost on Zeplik?
- Input tokens cost 1.7 credits per million and output tokens 6.6 credits per million (1 credit = $0.10; the raw provider rates are $0.15 and $0.60 per million). New accounts start with free credits.
- How long can a conversation with Llama 4 Maverick be?
- Llama 4 Maverick has a 1.0M-token context window (1,048,576 tokens), which covers the conversation plus any documents you attach.
- Does Llama 4 Maverick support images and tools?
- Llama 4 Maverick accepts image input and supports tool calling.
Related models
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...
Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and...