meta-llamatext + image → text
Meta: Llama 4 Scout
Canonical ID: meta-llama/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...
Artificial Analysis Benchmarks
VerifiedNo standardized Artificial Analysis benchmark scores recorded for this variant yet.
Token Pricing & Economics
Prompt Input (1M Tokens)
Input$0.10
Completion Output (1M Tokens)
Output$0.30
Prompt KV-Cache Read (1M Tokens)
Cached$0.00
Context Window Capacity
Context1,280k tokens
Supported Parameters & Features
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p