Llama 4 Scout 17B 128e Instruct API Pricing

Llama 4 Scout 17B 128e Instruct pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

What Llama 4 Scout 17B 128e Instruct costs in practice

1,000 requests with 2,000 input and 500 output tokens each

100 long-document requests with 100,000 input and 2,000 output tokens each

Llama 4 Scout 17B 128e Instruct features

Input: text, image. Output: text, code.

• Function calling

Use Llama 4 Scout 17B 128e Instruct with LiteLLM

Call Llama 4 Scout 17B 128e Instruct through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

from litellm import completion

response = completion(
    model="vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: llama-4-scout-17b-128e-instruct
    litellm_params:
      model: vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas
      vertex_project: os.environ/VERTEX_PROJECT
      vertex_location: os.environ/VERTEX_LOCATION

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "llama-4-scout-17b-128e-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Llama 4 Scout 17B 128e Instruct FAQ

More Meta models

• Llama 4 Maverick 17B$0.371 / $1.484 per 1M tokens
• Llama 4 Scout$0.10 / $0.30 per 1M tokens
• Llama 4 Maverick$0.20 / $0.60 per 1M tokens
• Llama 4 Maverick 17B 16e Instruct$0.35 / $1.15 per 1M tokens
• Llama 4 Maverick 17B 128e Instruct$0.35 / $1.15 per 1M tokens
• Llama 4 Scout 17B 16e Instruct$0.05 / $0.10 per 1M tokens
• Llama 3 70B Instruct Turbo$0.88 / $0.88 per 1M tokens
• Llama 3 8B Chat HF$0.20 / $0.20 per 1M tokens