Llama 4 Scout
by Metatext+image->text3 endpoints
Neura Intelligence Index
37.7/ 100
Rank
#235—
Confidence
lowBenchmarks
2(5% coverage)
Overview
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...
Capabilities
Text generation
Image understanding
Tool use / Function calling
Structured output
Long context
Top-P sampling
Stop sequences
Deterministic seed
Modalities
Input
TextImage
Output
Text
Technical Specifications
Context Window
1.3M tokens
Max Output
16.4K tokens
Knowledge Cutoff
2024-08-31
Tokenizer
Llama4
Uptime (24h)
9994.6%
Parameters
109000000000B
License
llama_4_community_license_agreementOpen Weights
Country
🇺🇸US
Release Date
April 5, 20251y
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Benchmark Performance
reasoning
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 57.2 | verified |
multimodal
| Benchmark | Score | Source |
|---|---|---|
| MMMU | 69.4 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$0.10
Output$0.30
Added
April 5, 2025
Last synced 9/18/2026