Hub/Models/meta-llama/llama-4-scout
meta-llamatext + image → text

Meta: Llama 4 Scout

Canonical ID: meta-llama/llama-4-scout

Compare ModelOpen on OpenRouter →

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...

Artificial Analysis Benchmarks

Verified
No standardized Artificial Analysis benchmark scores recorded for this variant yet.

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.10
Input
Completion Output (1M Tokens)
$0.30
Output
Prompt KV-Cache Read (1M Tokens)
$0.00
Cached
Context Window Capacity
1,280k tokens
Context

Supported Parameters & Features

frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p