Llama 4 Scout Instruct
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.
text + image → text · made by Meta
$0.1→$0.3per Mtok in / out
DeepInfra
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| DeepInfra 0 ways | $0.1per Mtok in$0.3per Mtok out | |
| DeepInfra aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.3per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Novita AI 0 ways | $0.18per Mtok in$0.59per Mtok out | |
| Novita AI aggregatornot on the seller's list today | standard | $0.18per Mtok in$0.59per Mtok outapi.novita.ai · read 2026-08-25 |
About
Llama 4 Scout Instruct — a text model from Meta.
It takes text and images and returns text, with a context window of 327,680 tokens. It was published in April 2025. The catalogue files it under chat.
Every current figure
- Maker
- Meta
- Register
- model
- Takes
- text + image
- Returns
- text
- Context
- 327,680 tokens
- Longest answer
- 131,072 tokens
- Published
- April 2025