Meta: Llama 4 Scoutmeta-llama
Bottom Line
Meta: Llama 4 Scout: $0.10/1M input, $0.30/1M output, 1.3M context, CPS grade B. Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
API Pricing (per 1M tokens)
| Input | $0.10 |
| Output | $0.30 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.15 |
Specs & Performance
| Context Length | 1.3M |
| Max Output | 16K |
| Intelligence | 7 |
| Coding | 8 |
| Math | 14 |
| Speed | 102 tok/s |
| TTFT | 0.64s |
| 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 Scout API cost?
Meta: Llama 4 Scout costs $0.10/1M input tokens and $0.30/1M output tokens. Blended cost at a 3:1 ratio is about $0.15/1M tokens.
What is the context window of Meta: Llama 4 Scout?
Meta: Llama 4 Scout supports a 1.3M token context window with up to 16K output tokens.
Is Meta: Llama 4 Scout worth it?
Meta: Llama 4 Scout has a CPS grade of B (score 55), intelligence index 7, coding index 8. Use the compare page to benchmark against rivals.