ModelPriceWatch.com
Last scan 2026-08-28 Models tracked 237 Providers 31 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

Llama 4 Scout vs Llama 4 Scout

Side-by-side comparison of API pricing, specs, benchmarks, and capabilities

Llama 4 Scout is 10.4% cheaper on blended cost ($0.150 vs $0.168/Mtok)
Specification
3 providers: Groq $0.110/$0.340 Meta $0.110/$0.340 DeepInfra $0.100/$0.300
by Meta
3 providers: Groq $0.110/$0.340 Meta $0.110/$0.340 DeepInfra $0.100/$0.300
Overview
StatusCurrent open weights Open weights Current open weights Open weights
Released Apr 6, 2025 Apr 6, 2025
Pricing per million tokens
Input $0.100/Mtok $0.110/Mtok
Output $0.300/Mtok $0.340/Mtok
Blended avg $0.150/Mtok $0.168/Mtok
Specifications
Context window 10M tokens 10M tokens
Parameters 17B (16 experts) 17B (16 experts)
Speed (TPS)
Modalities
Input
textimage
textimage
Benchmarks sources: Vellum LLM Leaderboard (Jun 2026), Meta model card / Vellum LLM Leaderboard
Avg benchmark score 46.8 46.8
Perf / dollar 312 279.4
GPQA Diamond 57.2 57.2
SWE-Bench Verified 28 28
LiveCodeBench 32.8 32.8
Humanity's Last Exam 12 12
ARC-AGI 2 15 15
AIME 2025 45 45
MMMLU 75 75
BFCL 58 58
HumanEval 80 80
MATH 500 65 65
Independent composite scores each on its own scale — not part of the average above
AA Intelligence Index 10.3 10.3
AA Agentic Index 1.1 1.1
AA-Omniscience Index (−100–100) -52.1 -52.1
Providers
Available from
Groq — $0.110/$0.340/Mtok
Meta — $0.110/$0.340/Mtok
DeepInfra — $0.100/$0.300/Mtok
Groq — $0.110/$0.340/Mtok
Meta — $0.110/$0.340/Mtok
DeepInfra — $0.100/$0.300/Mtok

Cost at scale

1M tokens · 50/50 input/output
Projected cost of Llama 4 Scout vs Llama 4 Scout at increasing token volumes
VolumeLlama 4 ScoutLlama 4 ScoutSavings
1M tokens $0.15 $0.17 $0.02 (11.9%)
10M tokens $1.5 $1.68 $0.17 (10.1%)
100M tokens $15 $16.75 $1.75 (10.4%)
1000M tokens $150 $167.5 $17.5 (10.4%)

When to pick which

distilled from the pricing and spec data above
Pick Llama 4 Scout if…
  • cost dominates: $0.150/Mtok blended vs $0.168 — 10.4% less on the same 50/50 token mix
Pick Llama 4 Scout if…
  • this pairing gives Llama 4 Scout no edge on price, context, cache discount, or measured performance — pick it only for qualitative fit (ecosystem, compliance, model behavior on your prompts)

Summary

Llama 4 Scout by DeepInfra costs $0.100/Mtok input and $0.300/Mtok output, with a 10M-token context window. It supports text, image input and is available from 3 providers.

Llama 4 Scout by Meta costs $0.110/Mtok input and $0.340/Mtok output, with a 10M-token context window. It supports text, image input and is available from 3 providers.

On a blended cost basis, Llama 4 Scout is 10.4% cheaper than Llama 4 Scout.

On benchmarks, Llama 4 Scout scores higher (46.8 vs 46.8) on average. In terms of value, Llama 4 Scout has better performance per dollar (312 vs 279.4).

Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.

More comparisons

pairs sharing a model with this page