LIVE Cheapest paid: Granite 4.0 Micro $0.017/Mtok in 173 models tracked Updated Jul 10, 2026
Jul 10, 2026
ModelPriceWatch$/Mtok
Pricing / Meta / Llama 4 Scout

Llama 4 Scout

by Meta · 17B (16 experts) parameters

Current open weights Open weights cheap tier

Pricing · per 1M tokens

Input
$0.110
per million tokens
Output
$0.340
per million tokens
Blended avg cost*$0.225/Mtok

Available on 3 hosts · cheapest first

Llama 4 Scout is sold by 3 providers. Prices are per 1M tokens (blended = avg of input & output). The first-party row is the model maker; “vs first-party” shows each host’s blended price relative to it.

Host Input Output Blended vs first-party
DeepInfra details → $0.100 $0.300 $0.200 -11%
Groq details → $0.110 $0.340 $0.225 0%
Meta first-party $0.110 $0.340 $0.225

Each host links to its provider page and official pricing. Prices refresh twice daily.

Overview

Meta's open-weight Llama 4 Scout — a natively multimodal MoE (17B active / 109B total, 16 experts) with an industry-leading 10M-token context, the longest of any open-weight model. Handles text, images, and video; fits on a single H100 with Int4. $0.11/$0.34 per 1M tokens.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

Input 2/5
Text ✓ Image ✓ Audio Video PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 3/9
Prompt caching Reasoning Coding Fast inference Long context ✓ Open weights ✓ Multimodal ✓ Web search Realtime

Benchmark performance

47.6%
avg benchmark score
211.6
perf / $/Mtok
GPQA Diamond
50%
AIME 2025
45%
SWE-Bench
28%
Humanity's Last Exam
12%
ARC-AGI 2
15%
MMMLU
75%
HumanEval
80%
MATH 500
65%
BFCL
58%
How it stacks up
  • Ranks #29 of 35 benchmarked models by average score
  • Ranks #4 of 35 comparably-tested models by normalized performance per dollar top value
  • Strongest at HumanEval — 80%, #45 of 64
Inference speed: 2600 tokens/sec

Source: Vellum LLM Leaderboard (Jun 2026), Meta model card · Updated Jun 9, 2026 · See full rankings →

Specifications

ProviderMeta
Context window10M tokens
Modalitytext, image
Parameters17B (16 experts)
Open sourceYes — open weights available
ReleasedApr 6, 2025
StatusCurrent
Last updatedJun 25, 2026
Tagsmultimodal open-weights moe

Cost calculator

1K tokens (in)$0.00011
1K tokens (out)$0.00034
100K tokens (in)$0.011
100K tokens (out)$0.034
1M tokens (in)$0.110
1M tokens (out)$0.340
10M tokens (blended)$2.25
Full calculator →

At a glance

Input$0.110/M
Output$0.340/M
Blended$0.225/M
Context10M
Tiercheap

Embed this price

A live, auto-updating badge for your README or docs:

Llama 4 Scout live API price

Price history

Last updated: Jul 10, 2026 · price links to the official provider pricing page (source above)

No price changes detected — this model's pricing has been stable since we began tracking it.

Compare Llama 4 Scout

Featured in these rankings

Related models