LLM Reference

Llama 4 Maverick 17B Instruct FP8 vs Llama 4 Scout 17B-16E Instruct

Llama 4 Maverick 17B Instruct FP8 (2025) and Llama 4 Scout 17B-16E Instruct (2025) are general-purpose language models from AI at Meta. Llama 4 Maverick 17B Instruct FP8 ships a 1m-token context window, while Llama 4 Scout 17B-16E Instruct ships a 10m-token context window. On MMLU PRO, Llama 4 Maverick 17B Instruct FP8 leads by 6.2 pts. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.

Llama 4 Scout 17B-16E Instruct is ~87% cheaper at $0.08/1M; pay for Llama 4 Maverick 17B Instruct FP8 only for vision-heavy evaluation.

Decision scorecard

Local evidence first
SignalLlama 4 Maverick 17B Instruct FP8Llama 4 Scout 17B-16E Instruct
Best formultimodal apps, long-context analysis, and provider-routed productionmultimodal apps, long-context analysis, and provider-routed production
Decision fitCoding, RAG, and AgentsCoding, RAG, and Agents
Context window1m10m
Cheapest output$0.60/1M tokens$0.30/1M tokens
Provider routes11 tracked12 tracked
Shared benchmarksMMLU PRO leader5 shared

Decision tradeoffs

Choose Llama 4 Maverick 17B Instruct FP8 when...
  • Llama 4 Maverick 17B Instruct FP8 holds a shared-benchmark lead on MMLU PRO, ahead by 6.2 points.
  • Local decision data tags Llama 4 Maverick 17B Instruct FP8 for Coding, RAG, and Agents.
Choose Llama 4 Scout 17B-16E Instruct when...
  • Llama 4 Scout 17B-16E Instruct has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • Llama 4 Scout 17B-16E Instruct has the lower cheapest tracked output price at $0.30/1M tokens.
  • Llama 4 Scout 17B-16E Instruct has broader tracked provider coverage for fallback and route flexibility.
  • Local decision data tags Llama 4 Scout 17B-16E Instruct for Coding, RAG, and Agents.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Lower estimate Llama 4 Scout 17B-16E Instruct

Llama 4 Maverick 17B Instruct FP8

$270

Cheapest tracked route/tier: OpenRouter

Llama 4 Scout 17B-16E Instruct

$139

Cheapest tracked route/tier: OpenRouter

Estimated monthly gap: $131. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

Llama 4 Maverick 17B Instruct FP8 -> Llama 4 Scout 17B-16E Instruct
  • Provider overlap exists on OpenRouter, Together AI, and Fireworks AI; start route-level A/B tests there.
  • Llama 4 Scout 17B-16E Instruct is $0.30/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
Llama 4 Scout 17B-16E Instruct -> Llama 4 Maverick 17B Instruct FP8
  • Provider overlap exists on Microsoft Foundry, Together AI, and OpenRouter; start route-level A/B tests there.
  • Llama 4 Maverick 17B Instruct FP8 is $0.30/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.

Specs

Specification
Released2025-04-052025-04-05
Context window1m10m
Parameters400B (17B active)109B (17B active)
ArchitectureMixture of ExpertsMixture of Experts
LicenseLlama 4 CommunityLlama 4 Community
OpennessOpen weightsOpen weights
WeightsUnknownUnknown
CodeUnknownUnknown
Commercial useCommercial use: conditionalCommercial use: conditional
Knowledge cutoff2024-082024-08

Pricing and availability

Pricing attributeLlama 4 Maverick 17B Instruct FP8Llama 4 Scout 17B-16E Instruct
Input price$0.15/1M tokens$0.08/1M tokens
Output price$0.60/1M tokens$0.30/1M tokens
Providers

Capabilities

CapabilityLlama 4 Maverick 17B Instruct FP8Llama 4 Scout 17B-16E Instruct
VisionYesYes
MultimodalYesYes
ReasoningNoNo
JSON / Tool useNoNo
Structured outputsYesYes
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

BenchmarkLlama 4 Maverick 17B Instruct FP8Llama 4 Scout 17B-16E Instruct
MMLU PRO80.574.3
LiveCodeBench43.432.8
Massive Multi-discipline Multimodal Understanding73.469.4
Chatbot Arena1365.01295.0
τ-bench68.562.3

Continue comparing

Last reviewed: 2026-07-09. Data sourced from public model cards and provider documentation.