Meta: Llama 4 Scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and…
meta-llama/llama-4-scout-17b-16e-instruct
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.
Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.
Specifications & capabilities
- Input
- text, image
- Output
- text
- Context window · tokens
- 1310720
- Knowledge cutoff
- 2024-08-31
- Published model ID
- Llama-4-Scout-17B-16E-Instruct
- Capabilities
- multimodal, structuredOutputs, toolCalling, visionInput
Description source ↗Evaluations
81–95 / 95
1,268.378
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Writing And Literature And Language
- dimension
- general
- metric
- Arena rating
- rank
- 273
- sample size
- 6696
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Llama 4 Scout 17B 16E Instruct
- confidence lower
- 1260.671144513681
- confidence upper
- 1276.0854030783344
Original result ↗1,248.913
- source id
- lmarena
- leaderboard name
- LMArena Text Creative Writing
- dimension
- general
- metric
- Arena rating
- rank
- 273
- sample size
- 3754
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Llama 4 Scout 17B 16E Instruct
- confidence lower
- 1238.9009534577085
- confidence upper
- 1258.9241215724319
Original result ↗1,241.896
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Entertainment And Sports And Media
- dimension
- general
- metric
- Arena rating
- rank
- 273
- sample size
- 5268
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Llama 4 Scout 17B 16E Instruct
- confidence lower
- 1233.3884751661076
- confidence upper
- 1250.4037796354764
Original result ↗1,285.736
- source id
- lmarena
- leaderboard name
- LMArena Text Coding
- dimension
- general
- metric
- Arena rating
- rank
- 276
- sample size
- 5222
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Llama 4 Scout 17B 16E Instruct
- confidence lower
- 1277.2029465475155
- confidence upper
- 1294.2683672006092
Original result ↗1,285.554
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Software And It Services
- dimension
- general
- metric
- Arena rating
- rank
- 276
- sample size
- 9488
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Llama 4 Scout 17B 16E Instruct
- confidence lower
- 1278.7327663076373
- confidence upper
- 1292.3749768356208
Original result ↗1,207.984
- source id
- lmarena
- leaderboard name
- LMArena Text Exclude Ties
- dimension
- general
- metric
- Arena rating
- rank
- 276
- sample size
- 21377
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Llama 4 Scout 17B 16E Instruct
- confidence lower
- 1201.3794181108424
- confidence upper
- 1214.587706368066
Original result ↗1,279.207
- source id
- lmarena
- leaderboard name
- LMArena Text Overall
- dimension
- general
- metric
- Arena rating
- rank
- 278
- sample size
- 29777
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Llama 4 Scout 17B 16E Instruct
- confidence lower
- 1274.492375449156
- confidence upper
- 1283.9206873570588
Original result ↗1,278.256
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Life And Physical And Social Science
- dimension
- general
- metric
- Arena rating
- rank
- 278
- sample size
- 4966
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Llama 4 Scout 17B 16E Instruct
- confidence lower
- 1269.2697256154393
- confidence upper
- 1287.2414252345338
Original result ↗1,266.001
- source id
- lmarena
- leaderboard name
- LMArena Text Hard Prompts
- dimension
- general
- metric
- Arena rating
- rank
- 278
- sample size
- 12883
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Llama 4 Scout 17B 16E Instruct
- confidence lower
- 1259.841837457437
- confidence upper
- 1272.1600265115965
Original result ↗1,264.745
- source id
- lmarena
- leaderboard name
- LMArena Text Longer Query
- dimension
- general
- metric
- Arena rating
- rank
- 281
- sample size
- 5795
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Llama 4 Scout 17B 16E Instruct
- confidence lower
- 1256.4279615549708
- confidence upper
- 1273.06170714769
Original result ↗1,252.223
- source id
- lmarena
- leaderboard name
- LMArena Text Non English
- dimension
- general
- metric
- Arena rating
- rank
- 281
- sample size
- 16748
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Llama 4 Scout 17B 16E Instruct
- confidence lower
- 1246.512811363521
- confidence upper
- 1257.9339531474495
Original result ↗1,247.635
- source id
- lmarena
- leaderboard name
- LMArena Text Instruction Following
- dimension
- general
- metric
- Arena rating
- rank
- 285
- sample size
- 7470
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Llama 4 Scout 17B 16E Instruct
- confidence lower
- 1240.3179947635601
- confidence upper
- 1254.951803212571
Original result ↗8.2
- source id
- artificialAnalysis
- dimension
- coding
- metric
- Coding Index
Original result ↗6.5
- source id
- artificialAnalysis
- dimension
- intelligence
- metric
- Intelligence Index
Original result ↗0.5
- source id
- artificialAnalysis
- dimension
- agentic
- metric
- Agentic Index
Original result ↗Published prices
1–6 / 6
$0.27
- Inference provider
- cloudflareWorkersAI
- Platform
- Cloudflare Workers AI
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing label
- per M input tokens
$0.85
- Inference provider
- cloudflareWorkersAI
- Platform
- Cloudflare Workers AI
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing label
- per M output tokens
$0.10
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- input_tokens_per_million
- Currency
- USD
$0.30
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- output_tokens_per_million
- Currency
- USD
$0.10
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.30
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
Provider specifications & access
1–3 / 3
- source model id
- @cf/meta/llama-4-scout-17b-16e-instruct
- hosting
- cloudflare-hosted
- context length
- 131000
- source model id
- publishers/hf-meta-llama/models/llama-4-scout-17b-16e-instruct@001
- hosting
- vertex-self-deployed
- source model id
- publishers/meta/models/llama4@llama-4-scout-17b-16e-instruct
- hosting
- vertex-self-deployed
Safety assessments
1–1 / 1
31 / 100
- source id
- stanfordFMTI
- canonical model id
- meta-llama/llama-4-scout-17b-16e-instruct
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- Meta
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 31 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–3 / 3
- field
- context_length
- value
- 1310720
- normalized value
- 1310720
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2024-08-31
- normalized value
- 2024-08-31
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- openRouter
- confidence
- 1
Explore more models