Meta

Llama 4 Scout

Vérifié par l’équipe de recherche de GetInfoUsDernière révision : October 2026Politique éditoriale
Roi du contexte 10MOfficial Source Verified ↗
76
Intelligence Index

monde-record à long contexte ouvert modèle supporting ~3.5 millions tokens pour complet codebase et vidéo library ingestion.

Technical Specifications

Provider
Meta
Category
open-source
Release Date
2025-04
Knowledge Cutoff
January 2025
Architecture
Extreme-context sparse MoE multimodal transformer (17B active / 109B total)
Parameters
17B (109B total MoE)
Context Window
3.5M tokens
Max Output
33K tokens
Cached Input Price
$0 / 1M tokens
Batch API Discount
Standard rate
Consumer Subscription
Free / Self-Hosted
Reasoning Mode
No (Standard)
Reasoning Effort Control
Fixed
Tool Calling
Yes
Structured Outputs
Yes
Open Weights
Yes (Open Source / Self-Hostable)
Input Modalities
text, vision
Output Modalities
text
Official Documentation
Visit Official Docs ↗

Data Privacy, Licensing & Deployment Governance

API Data Training Policy
100% Isolated when self-hosted on private GPUs or VPC
Model License & Commercial Rights
Llama Community License (Commercial Permitted)
Deployment & Cloud Availability
Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API
Output Ownership
Full commercial ownership of generated outputs

Official Provider Release Intelligence, API Quotas & Agentic Specs

Compare Multi-Models Side-by-Side →
Official API Model ID (SDK String)
meta-llama/Llama-4-Scout
Supported SDK & API Protocol
OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
Lifecycle & Deprecation Status
Active GA (Guaranteed support through 2027+)
Production Rate Limits (RPM & TPM)
Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
Long-Context Pricing Tier (>128K / >200K)
Free across full context window (only KV-cache VRAM scales)
Prompt Cache Write & TTL Policy
Automatic prefix KV-caching in vLLM / SGLang (0 cost)
Computer Use & Browser GUI Agent
API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
MCP & Parallel Tool Calling
Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
Web Search Grounding & Code Sandbox
Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
Fine-Tuning & Distillation Support
Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
Multimodal Tokenization Billing
Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile)
Weights Precision & Quantization
BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
Minimum GPU VRAM Requirement
11 GB VRAM (4-bit Quantized) · 37 GB VRAM (Native BF16)
Supported Inference Engines
vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
System Card & Safety Framework
Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
Enterprise Compliance (SOC2 / HIPAA / ZDR)
100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Engineering & Pricing Workbench

Llama 4 Scout Cost, Context, Hardware & API Integration

500 / day
4,000 tok
1,000 tok
Conversation Depth (History Re-billing):1 Turn (Single-Shot)
50%
Estimated Monthly API Cost (30 Days)
Free ($0)
Subscription ($20/mo) vs API

Open-weights or free-tier model: $0 API license cost when self-hosted.

Same Monthly Workload Cost Across Popular Reference Models

Llama 4 Scout (Active)
$0.00
/ month
Gemini 2.5 Flash
$18.00
/ month
DeepSeek V3
$32.70
/ month
GPT-4o
$300.00
/ month
Claude 3.7 Sonnet
$405.00
/ month

Live Prompt Paste Tokenizer & Cost Counter

Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.

Chars / Words
175 / 24
OpenAI o200k
~46 tok
Claude BPE
~49 tok
Llama / DeepSeek
~51 tok

Hybrid Prompt Routing Cascade Simulator

Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Llama 4 Scout:

Cascaded Monthly Bill:$13.50/mo
This model is already priced at or below the fast router baseline.

Benchmark Scores & 6-Axis Capability Radar

Benchmark Encyclopedia
Coding (86)Reasoning (76)Knowledge (78)Speed (63)Context (100)Cost Value (98)
Llama 4 Scout2026 Frontier Median
MMLU-Pro
78%
HumanEval
86%
Long-Context Reasoning
92.5%
Chatbot Arena Elo
1370pts

Strengths

  • Colossal 3.5 millions token fenêtre de contexte
  • Sparse MoE architecture keeps actif compute à seulement 17B
  • à poids ouverts available pour local déploiement

Limitations & Trade-offs

  • nécessite élevé unified mémoire à store le complet 109B weights
  • Secondary raisonnement profondeur par rapport à dense raisonnement modèles

Editorial Assessment

le undisputed king de massif open source contexte windows dans 2025.

Best for: Whole-dépôt code analyse, multi-hour vidéo compréhension, et juridique book ingestion

Frequently Asked Questions about Llama 4 Scout

How much does the Llama 4 Scout API cost per 1M tokens?+

Llama 4 Scout by Meta is priced at $0 per 1M input tokens and $0 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0 per 1M tokens, and asynchronous Batch API requests receive a 0% discount.

Should I use a $20/month subscription or the Llama 4 Scout pay-as-you-go API?+

A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.

How many words and pages fit in Llama 4 Scout's context window?+

Llama 4 Scout features a 3.5M tokens context window, which equals approximately 2,625,000 English words or ~7,000 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 32,768 tokens.

Can I run Llama 4 Scout locally on my own GPU (Open Weights)?+

Yes, Llama 4 Scout (17B (109B total MoE)) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.

Does Meta train on data sent to the Llama 4 Scout API, and is commercial use allowed?+

100% Isolated when self-hosted on private GPUs or VPC. License tier: Llama Community License (Commercial Permitted). Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.

How does Llama 4 Scout perform on coding and reasoning benchmarks?+

Llama 4 Scout achieves a composite Intelligence Index of 76/100, scoring N/A% on SWE-bench Verified, N/A% on GPQA Diamond, 78% on MMLU-Pro, and 1370 pts on Chatbot Arena Elo.

What is Llama 4 Scout best used for?+

Llama 4 Scout is best suited for: Whole-dépôt code analyse, multi-hour vidéo compréhension, et juridique book ingestion. Assessment: le undisputed king de massif open source contexte windows dans 2025.

Les scores de benchmarks, tarifs par token et limites évoluent rapidement. Vérifiez toujours les spécifications actuelles sur la documentation officielle du fournisseur.

Sources: Meta AI Llama 4 Research Announcement↗