Meta: 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...
Specification
- Model ID
- meta-llama/llama-4-maverick
- Weight license
- Not verified; consult the exact publisher model card
- Modality
- Text+image >text
- Context
- 524.3K tokens
- Input
- $0.350/1M
- Output
- $1.00/1M
- Updated
- Nov 14, 2026
Scores
Capabilities
- Supports tool calling
- Supports vision inputs
- Supports long-context workflows
- Lighter reasoning profile
Input and output
Accepts Text, Image inputs. Returns Text outputs.
Supported parameters
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Related models
Build with Meta: Llama 4 Maverick
Describe what you want to make and pick this model in the composer. A database and hosting are included.