Meta Pro · $9/month 10 tokens / message Balanced

Meta: Llama 4 Scout · Meta

Meta Llama 4 Scout 17B Instruct is a mixture-of-experts language model that activates 17 billion parameters from a total of 109B. It features native multimodal capabilities with an extended context of 1,310,720 tokens for complex conversations and deep analysis.

Ultra-long 1.3M token context Efficient MoE architecture Native multimodal capabilities

Try it free

Meta: Llama 4 Scout requires the Pro plan

Create a free account to start, or subscribe to a plan for unlimited use of premium models.

No card to start · Cancel anytime

Open in full chat → Compare models side by side, save your sessions and memory

About Meta: Llama 4 Scout

Meta Llama 4 Scout 17B Instruct is a mixture-of-experts language model that activates 17 billion parameters from a total of 109B. It features native multimodal capabilities with an extended context of 1,310,720 tokens for complex conversations and deep analysis.

Where it shines: Ultra-long 1.3M token context · Efficient MoE architecture · Native multimodal capabilities.

How to use Meta: Llama 4 Scout

  1. 1

    Type or upload

    Type what you want in the box above — or upload the file if the tool asks for one.

  2. 2

    Generate

    Click the main button. Wait 2-30 seconds depending on the model and input size.

  3. 3

    Download or share

    Download the result or share the direct link. No watermark, ready to use.

Frequently asked questions

How much does it cost to use Meta: Flame 4 Scout?

Meta: Llama 4 Scout is a Pro model: it costs 10 tokens per use (~$0.05 real cost for us). You need a Pro plan ($9/month → 15,000 tokens) or a one-shot pack. If you already have tokens in the free account, you can also spend them directly.

How many uses of Meta: Flame 4 Scout are included in the Pro plan?

Pro ($9/month) gives you 15,000 recurring tokens. At 10 tokens per use of Meta: Call 4 Scout, that's ~1,500 full uses per cycle. If you run out, one-shot packs (5,000 / 25,000 / 80,000 tokens) add to the balance without expiring before one year.

What makes Meta: Flame 4 Scout special?

Meta publishes the full weights of the Llama family — well-proven in general chat, code and multilingual. Its specific strengths are: ultra-extensive context 1.3m tokens, moe-efficient architecture and native multimodal capabilities. It accepts images as input (multimodal) as well as text — useful for describing captures, reading graphs or solving problems from a photo.

How fast does Meta: Llama 4 Scout respond?

Goal: Llama 4 Scout has a balanced speed: 5-15 seconds per response — neither the fastest nor the slowest in the catalog. Actual time depends also on the length of the prompt and the load of the datacenter — models with huge context take longer when you enter very long texts.

How do I use Meta: Flame 4 Scout in ia.gratis?

You can use Meta: Call 4 Scout from /chat/ by selecting Meta: Call 4 Scout in the picker, or via the REST API with `model=call-4-scout` in the POST body. Quick summary: call 4 Scout: Meta multimodal model with 17B active parameters and 1.3M context. The internal model identifier is `call-4-scout` — useful when integrating by API.