Llama 4 Scout
Meta · released 5 Apr 2025 · open weights
- Cheapest frontier model to run
- Open weights, self-hostable
Smaller open-weights MoE (17B active, 16 experts) that fits on a single H100; the cheapest row in this ledger.
Context window
320K
320,000 tokens
Input price
$0.10
per 1M tokens
Output price
$0.30
per 1M tokens
Blended
$0.15
3:1 in:out mix
Weights
Open
self-hostable
Released
5 Apr 2025
Meta
Long-context / tier pricing — Meta specs a 10M window; the rate shown is DeepInfra's, which serves 320K of it. Listed prices are the base rate for prompts up to ~200K tokens.
Open-weights API prices are representative third-party-hosted rates; self-hosting costs only your own hardware.
Where it ranks
Of 29 models tracked.
Cost to run
#1
of 29
Input price
#1
of 29
Context window
#24
of 29
Compare with
The nearest models by blended cost to run.
Put it to work
Specs from BitByteCore's hand-verified Frontier Ledger (v2026-09-15), this row verified 15 Sep 2026 against DeepInfra's listed price ↗. Model pricing moves fast, so confirm with DeepInfra before you rely on a figure.