AI Observatory / Model Radar
Meta / meta-llama/llama-4-maverick
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...
1,048,576
Context
16,384
Max output
$0.15 / 1M
Prompt price
2025-04-05
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Meta | Input modalities | text, image |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.15 / 1M |
| Completion price | $0.60 / 1M | Request price | N/A |
| Context length | 1,048,576 | Max completion tokens | 16,384 |
| Supported parameters | frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_p | ||
Best for
meta-llama/llama-4-maverick
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...
Cross-modal work
Long context
High-volume usage
vision
long-context
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.