Meta: Llama 4 Maverickmeta-llama
Bottom Line
Meta: Llama 4 Maverick: $0.19/1M input, $0.65/1M output, 524K context, CPS grade B. 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...
API Pricing (per 1M tokens)
| Input | $0.19 |
| Output | $0.65 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.30 |
Specs & Performance
| Context Length | 524K |
| Max Output | 16K |
| Intelligence | 9 |
| Coding | 16 |
| Math | 19 |
| Speed | 54 tok/s |
| TTFT | 0.59s |
| CPS Grade | B |
| Input / Output Modalities | text, image → text |
More from meta-llama
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Meta: Llama 4 Maverick API cost?
Meta: Llama 4 Maverick costs $0.19/1M input tokens and $0.65/1M output tokens. Blended cost at a 3:1 ratio is about $0.30/1M tokens.
What is the context window of Meta: Llama 4 Maverick?
Meta: Llama 4 Maverick supports a 524K token context window with up to 16K output tokens.
Is Meta: Llama 4 Maverick worth it?
Meta: Llama 4 Maverick has a CPS grade of B (score 57), intelligence index 9, coding index 16. Use the compare page to benchmark against rivals.