# Llama 4 Maverick 17B 128E Instruct API prices

Llama 4 Maverick 17B 128E Instruct (llama) — 524k context, 8k max output.
2 metered per-token offers from 3 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| IO.NET | $0.15 | $0.6 | $0.075 | 430k |
| Vertex | $0.35 | $1.15 | — | 524k |

## Summary

- Cheapest input: $0.15 per 1M tokens (IO.NET)
- Cheapest output: $0.6 per 1M tokens (IO.NET)
- First-party: not listed separately
- Free offers: Nvidia
- Subscription plans (not per-token): none
- Released: 2025-01-15
- Inputs: image, text

HTML page: https://llmprice.gitlab.io/models/llama-4-maverick-17b-128e-instruct/
Full dataset: https://llmprice.gitlab.io/data/catalog.json