Llama 4 Scout

meta/llama-4-scoutopen weightsimages

Try in playground Get API key

Input

$0.1

per M tokens

Output

$0.3

per M tokens

Cache read

—

not offered on this model

Context

327K

tokens

Pricing

Input	$0.1 / M tokens
Output	$0.3 / M tokens
Routing	Free

Provider list price. BYOK requests bill on your own provider account; managed credits draw down at exactly these rates. No markup, no request fee. Every request is metered per engineer and joined to the work it shipped.

Run it

Claude Code

export ANTHROPIC_BASE_URL=https://api.tokenspend.dev
export ANTHROPIC_API_KEY=$TOKENSPEND_RAIL_KEY
export ANTHROPIC_MODEL=meta/llama-4-scout

curl

curl https://api.tokenspend.dev/v1/messages \
  -H "content-type: application/json" \
  -H "x-api-key: $TOKENSPEND_RAIL_KEY" \
  -d '{"model":"meta/llama-4-scout","max_tokens":256,"messages":[{"role":"user","content":"hello"}]}'

Python · OpenAI SDK

from openai import OpenAI

client = OpenAI(base_url="https://api.tokenspend.dev/v1", api_key=os.environ["TOKENSPEND_RAIL_KEY"])
resp = client.chat.completions.create(
    model="meta/llama-4-scout",
    messages=[{"role": "user", "content": "hello"}],
)

Both dialects reach every model: send Anthropic-shaped requests or OpenAI-shaped requests and the rail translates. Prompts and responses are never stored.