Meta logo

Llama 4 Scout

Pricing & Specs API
Free REST API for prices, specs and benchmarks
Llama 4 Scout is Meta's language model with a 1.3M context window and up to 16K output tokens, available from 4 providers, starting at $0.1 / 1M input and $0.3 / 1M output. Meta's Llama 4 Scout MoE LLM with 17B active parameters and 16 experts, offering efficient multimodal inference with native image and text support.
Specifications
Canonical IDmeta-llama-4-scout
TypeLanguage
StatusActive
CreatorMetaMeta
Providers
Context Window1.3M tokens
Max Output16K tokens
Input ModalitiesImageText
Output ModalitiesText
Parameters109B
HuggingFace Likes1,274
HuggingFace Downloads (30d)399,353
HuggingFace Downloads (all-time)5,433,902
Release Date · 1 year ago
Knowledge Cutoff · 2 years ago
Benchmarks
Intelligence Index
10.3
#304
Coding Index
8.2
#153
Math Index
14.0
#214
MMLU-Pro
0.8
#162
GPQA
0.6
#298
HLE
0.0
#423
LiveCodeBench
0.3
#206
AIME
0.3
#79
IFBench
0.4
#241
Time to First Token
0.61s
#420
SciCode
0.2
#393
MATH-500
0.8
#87
AIME 2025
0.1
#214
LCR
0.3
#248
TerminalBench Hard
0.0
#325
TAU2
0.2
#338
Output TPS
116.7
#61

Capabilities

Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Google Gemini logo
Google Gemini
llama-4-scout
$0.25$0.7$0.125$0.35
Google Vertex AI logo
Google Vertex AI
llama-4-scout
$0.25$0.7$0.125$0.35
OpenRouter logo
OpenRouter
meta-llama/llama-4-scout
$0.1$0.3——
Vercel AI Gateway logo
Vercel AI Gateway
meta/llama-4-scout
$0.17$0.66——

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Llama 4 Scout, ranked by cheapest on-demand price. The model needs about 261 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
g7e.24xlargeAWS4× RTX PRO Server 6000384 GB$16.57/hrus-east-1
g4-standard-192GCP4× nvidia-rtx-pro-6000384 GB$18.00/hrus-central1
p4d.24xlargeAWS8× A100320 GB$21.96/hrus-west-2
7 more instances can run Llama 4 Scout
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
LlamaGuard 4 12B1.0M$0.180$0.180Available
Llama 4 Scout1.3M$0.100$0.300Current
Llama 4 Maverick1.0M$0.120$0.485Available

Model IDs

llama-4-scout
meta-llama-4-scout
meta-llama/llama-4-scout
meta/llama-4-scout
vercel_ai_gateway/meta/llama-4-scout