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...
Everything else
| Max output | 16K |
|---|---|
| Input / 1M | $0.2 |
| Output / 1M | $0.8 |
| Cache read / 1M | — |
| Cache write / 1M | — |
| 1M in + 1M out | $1 |
| Takes | text, image |
| Returns | text |
| Tools | yes |
| Reasoning | no |
| Open weights | yes |
| Released | 2025-04-05 |
| Knowledge cutoff | 2024-08-31 |
| Retires | — |
| Catalog id | meta-llama/llama-4-maverick |
Benchmarks
| source | epoch |
|---|---|
| eci | 133.03 |
| confidence | Likely |
| accessibility | Open weights (restricted use) |
Benchmark scores by Epoch AI, CC BY 4.0.
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.