Llama 4 Scout

1.05M ctxTextImage Tools

Released Apr 5, 2025 · 87B tokens this week · 5 providers

Overview

The smaller Llama 4 mixture-of-experts, built for long-context retrieval on modest hardware. Cheap, fast and multimodal, with quality close to the previous generation of dense 70B models. A sensible default for document-heavy pipelines on a budget.

translationroleplayagents

Providers

Reference data — not yet measured from live traffic

PROVIDER		MAX OUT		OUTPUT /M				QUANT
DeepInfraCheapest	1.05M	16K	$0.11	$0.34	400ms	155	98.90%	fp8
Novita AI	328K	16K	$0.12	$0.37	460ms	128	98.50%	fp8
Groq	131K	16K	$0.12	$0.38	209ms	620	99.85%	Full
Together AI	1.05M	16K	$0.13	$0.39	195ms	190	99.48%	Full
Amazon Bedrock	131K	16K	$0.13	$0.41	560ms	130	99.76%	Full

Latency p50 reflects a provider’s API endpoint responsiveness — the round-trip to its API, not per-token inference time. These figures, with throughput and uptime, are reference data until the gateway aggregates its own traffic.

Price comparison

Blended $ per 1M tokens

Llama 4 Scout$0.28

DeepSeek V3.2$0.37

Gemini 3 Flash$1.95

GPT-5.2$10.94

Claude Sonnet 4.5$12.00

Blended rate per 1M tokens, weighted one part prompt to three parts completion — roughly the shape of a chat workload. Your mix will move the number.

Call it

OpenAI-compatible — swap the base URL and go

curl https://model.cards/api/v1/chat/completions \
  -H "Authorization: Bearer $MODELCARDS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-4-scout",
    "messages": [
      { "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
    ]
  }'