Llama 4 Scout 17B 16e Instruct

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

Meta· 131K ctx

open weightsstructured quant: unknown

spread (output, p90 ÷ p10)

1.3×

$0.300 – $0.850 · 5 providers · max÷min 2.8×

5 providers priced · 5 offerings

Including routers & resellers

Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.

Provider classes in the stats:

Blended $/M assumptionsInput : output: 1Cache-hit share of input%

blended = 90.9% input × [(1 − 70% cache) × input + 70% cache × cache-read] + 9.1% × output + cache writes (30% of uncached input) where a write price is published

A provider that publishes no cache price is blended with cache share 0 (all input at the input price) and labelled “no cache price published” — never penalised against identical in/out prices.

Provider	Input	Output	Cache rd	Blended
Deep Infraoutlier inference host	$0.100	$0.300	—	$0.118no cache price published
NovitaAI inference host	$0.180	$0.590	—	$0.217no cache price published
Azure hyperscaler	$0.200	$0.780	—	$0.253no cache price published
Azure Cognitive Services hyperscaler	$0.200	$0.780	—	$0.253no cache price published
Cloudflare Workers AI inference host	$0.270	$0.850	—	$0.323no cache price published

Unpriced · 1

Listed at $0 with no published pricing — we can't tell whether it's free, bundled or just missing. Excluded from cheapest, median and spread.

Llama llama-4-scout-17b-16e-instruct-fp8unpriced

Connect

Provider (default: cheapest output among direct providers)

$0.300 /M · inference host

opencode.json

{
  "provider": {
    "deepinfra": {
      "npm": "@ai-sdk/deepinfra",
      "models": {
        "meta-llama/Llama-4-Scout-17B-16E-Instruct": {}
      }
    }
  }
}

Set DEEPINFRA_API_KEY in your environment. Generated — verify against the OpenCode docs.

Output $/M over time7-day preview

Median line, min–max band. Pre-2026-09 points are catalog-recorded dates from models.dev git history, not provider effective dates.

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.