ModelPriceWatch.com
Last scan 2026-11-07 Models tracked 308 Providers 42 Cheapest paid pplx-decider-flash-v1.2 $0.010/Mtok in Every price links to its source

Llama 4 Scout

by Meta · 17B (16 experts) parameters

Retired open weights open weights cheap tier
Email me when Llama 4 Scout gets cheaper
Retired on . No longer served on the endpoint we price — the figures below are kept for historical reference only.
Availability: Meta does not sell this model per token; its developer rate card (dev.meta.ai/docs/pricing-rate-limits) prices only Muse models. The price on this row was Groq's, and Groq shut meta-llama/llama-4-scout-17b-16e-instruct down for self-serve accounts on 2026-07-17 (console.groq.com/docs/deprecations; enterprise contracts are excepted). The same price on Groq's own row, groq-llama-4-scout, has been Retired since then. The rate shown is the last public per-token price Groq charged, and you can no longer buy it. Llama 4 Scout is still sold per token by other hosts; see deepinfra-llama-4-scout.

Today's price · per 1M tokens

Input

$0.110

per 1M tokens

Output

$0.340

per 1M tokens

Blended

$0.168

blended $/1M — 3:1 weighted input:output

Source: official Meta pricing · read MODELPRICEWATCH.COM · 2026-11-07

Price receipt

Historical price.This model is retired — withdrawn on — so the provider no longer sells it and its page can no longer confirm this number: a price for a model no longer on sale is unconfirmable by definition, not missing. The figures above are the last prices we recorded for this model, kept as a historical record rather than a live quote.

Llama 4 Scout is still sold by DeepInfra at $0.150 blended per 1M tokens — see the consolidated Llama 4 Scout page →

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.

RunPod →
Rent GPUs by the second and serve any open-weight model yourself.
Novita AI →
Serverless open-model inference billed per token — no GPU ops.
Vast.ai →
GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

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

struck through = not supported
Input 2/4
Text ✓ Image ✓ Audio Video
Output
Text ✓
Features 3/9
Prompt caching Reasoning Coding Fast inference Long context ✓ Open weights ✓ Multimodal ✓ Web search Realtime

Benchmark performance

accuracy % · higher is better
Avg benchmark score46.8%
Perf per $/Mtok279.4
GPQA Diamond
57.2%
SWE-Bench Verified
28%
LiveCodeBench
32.8%
Humanity's Last Exam
12%
ARC-AGI 2
15%
AIME 2025
45%
MMMLU
75%
BFCL
58%
HumanEval
80%
MATH 500
65%
Independent composite scores
  • AA Intelligence Index: 6.5 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • AA-Omniscience Index: -52.1 (−100–100)
  • GDPval-AA v2: -155.8 ELO (Real-world work tasks, human baseline = 1000)
How it stacks up
  • Ranks #81 of 100 benchmarked models by average score
  • Ranks #160 of 194 comparably-measured models by percentile score, across 13 independent measurements
  • Ranks #26 of 194 comparably-tested models by normalized performance per dollar
  • Strongest at HumanEval — 80%, #24 of 47

2600 tokens/sec output 0.33s latency to first token (TTFT)

Source: Vellum LLM Leaderboard · updated · See full rankings →

Specifications

Provider
Meta
Context window
10M tokens
Modality
text, image
Parameters
17B (16 experts)
Open source
Yes — open weights available
Released
Status
Retired ended
Last updated
Tags
multimodalopen-weightsmoeretired

Availability verified: — per Meta's own deprecation notice

Official pricing page