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

Meta: Llama 4 Maverick

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

Compare ModelOpen on OpenRouter →

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

Artificial Analysis Benchmarks

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

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.35
Input
Completion Output (1M Tokens)
$1.00
Output
Prompt KV-Cache Read (1M Tokens)
$0.17
Cached
Context Window Capacity
512k tokens
Context

Supported Parameters & Features

frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p