LLM Reference

Llama 4 Scout 17B Instruct

llama-4-scout-17b-instruct

Researched 2d ago

Last refreshed 2026-05-19. Next refresh: weekly.

ProprietaryMultimodalCodingRAGLong contextVisionClassificationJSON / Tool use

Llama 4 Scout 17B Instruct is worth evaluating for coding, rag, and long context when its provider route and context window match the workload.

Decision context: Coding task fit, 1 tracked provider route, and research from 2026-05-19.

Use it for

  • Teams evaluating coding, rag, and long context
  • Workloads that can use a 10M context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Workloads where another current model has stronger sourced task evidence

Cheapest output

$0.660

AWS Bedrock per 1M tokens

Provider routes

1

Tracked API hosts

Quality / dollar

Grade C

Ranked by benchmark score divided by cheapest output price

Freshness

2026-05-19

Researched 2d ago

fresh

Top use-case fit

Coding

Q/$ C

1 relevant benchmark in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Provider price ladder

ProviderInput / 1MOutput / 1MBatch in / outRoute
AWS Bedrock$0.170$0.660$0.085 / $0.330
Serverless

Benchmark peer barsfor Coding

Migration checks

No linked migration route is available for this model yet.

About

Llama 4 Scout 17B Instruct is Meta's Llama 4 model with multimodal text and image input. It scores 1295 on the Chatbot Arena benchmark.

Llama 4 Scout 17B Instruct has a 10M-token context window.

Llama 4 Scout 17B Instruct input tokens at $0.17/1M, output at $0.66/1M.

Capabilities

MultimodalStructured Outputs

Benchmark Scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Chatbot Arena1295.0https://lmarena.ai
Massive Multi-discipline Multimodal Understanding69.4https://ai.meta.com/blog/llama-4-scout-maverick/
MMLU PRO74.3https://ai.meta.com/blog/llama-4-scout-maverick/
LiveCodeBench32.8https://ai.meta.com/blog/llama-4-scout-maverick/

Rankings

Specifications

FamilyLlama 4
Released2025-04-05
Context10M
Knowledge cutoff2024-08

Created by

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website

Providers(1)