Meta: Llama 4 Maverick
Released Apr 5, 2025Try it on:
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...
Best overall rank
-
Across all subsets · overall
Total arena votes
0
Across 0 (subset, category) entries
Providers on OR
0
None yet
First seen
-
Awaiting first snapshot
Trend
No snapshot history yet - trends appear after the first daily refresh.
Pricing
Per token
- Input (per 1M)
- $0.150
- Output (per 1M)
- $0.600
Capabilities
Modality
text+image->textContext
1M tokens
Tokenizer
Llama4
Knowledge cutoff
2024-08-31
Max output
16K tokens
Moderation
Unmoderated
Hugging Face
Supported parameters
frequency_penalty
logit_bias
max_tokens
min_p
presence_penalty
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_p
Providers
No provider endpoint data yet.
Per-category ranks
No leaderboard entries for this model.