llama-4-scout-17b-16e-instruct

Text Generation · Meta · Hosted

llama-4-scout-17b-16e-instruct

Meta's Llama 4 Scout is a 17 billion parameter model with 16 experts that is natively multimodal. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

BatchFunction callingVision

Model Info

Task Type

Text Generation

Author

Meta

Endpoint

/api/v1/chat/completions

Terms and License

link

Function calling

Yes

Reasoning

Vision

Yes

Unit Pricing

$0.27 per M input tokens, $0.85 per M output tokens

Playground

Try this model

Use the marketplace playground with this public slug.

Open Playground

Usage

curl

curl https://devix.one/api/v1/chat/completions \
  -H "Authorization: Bearer mak_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "llama-4-scout-17b-16e-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Explain this model in one sentence."
    }
  ],
  "max_tokens": 256
}'

Parameters

Request Body

{
  "model": "llama-4-scout-17b-16e-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Explain this model in one sentence."
    }
  ],
  "max_tokens": 256
}

Response

Text models return OpenAI-compatible chat completions. Image models return data[0].url. Other model types return a normalized result object.

Internal credentials and routing fields are never exposed here.

API Schemas (Raw)

json

{
  "model": "string",
  "messages": [
    {
      "role": "system | user | assistant",
      "content": "string"
    }
  ],
  "max_tokens": "number | optional",
  "stream": "boolean | optional"
}