meta-llamatext + image → text
Meta: Llama 4 Maverick
Canonical ID: meta-llama/llama-4-maverick
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
VerifiedNo standardized Artificial Analysis benchmark scores recorded for this variant yet.
Token Pricing & Economics
Prompt Input (1M Tokens)
Input$0.35
Completion Output (1M Tokens)
Output$1.00
Prompt KV-Cache Read (1M Tokens)
Cached$0.17
Context Window Capacity
Context512k tokens
Supported Parameters & Features
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p