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...
The figures
- Made by
- Meta
- Model ID
- meta-llama/llama-4-maverick
- Input
- $0.188 per million tokens
- Output
- $0.653 per million tokens
- Context window
- 1.05M tokens
- Longest answer
- 16K tokens
- Takes in
- text, image
- Gives back
- text
- Reasoning
- No
- Tool calling
- Yes
- Reads images
- Yes
- Open weights
- Yes
- Released
- 5 Apr 2025
Read on 3 Oct 2026.