# Llama 4 Maverick — price & specs

Source: https://modelbank.ai/models/llama-4-maverick · updated 2026-11-12 · ModelBank

| Field | Value |
|---|---|
| Vendor | Meta Llama |
| Input price | $0.35 / 1M tokens |
| Output price | $1 / 1M tokens |
| Cached input | $0.17 / 1M tokens |
| Context window | 524,288 tokens |
| Max output | 32,768 tokens |
| Input modalities | text,image |
| Reasoning / tool use | no / yes |
| Intelligence / coding index | — / 16.3 |
| Released | 2025-04-05 |
| Retirement date | none announced |

## About

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...

## Price history

- 2026-09-24: $0.19 in / $0.65 out
- 2026-11-06: $0.35 in / $1 out


JSON: https://modelbank.ai/api/v1/models/llama-4-maverick