What is Llama 4 Scout good for?

Text and image work over an extremely long context. Open weights under the Llama 4 Community License, servable on a single high-memory GPU.

When is Llama 4 Scout not a good fit?

Video input and structured output, which it has neither of. Memory follows the full 109B parameters, not the 17B active, so it takes more than Meta's dense 70B Llamas.

What is the cheapest way to run Llama 4 Scout?

Hosted, unless you push serious volume. Azure charges $0.16 in / $0.64 out per 1M tokens. The cheapest rental that fits is 8x RTX 3060 at $346 a month, which costs the same as about 1B tokens a month on that API.

Can I self-host Llama 4 Scout?

Yes. The weights are released under the Llama 4 Community License. At 4-bit it needs about 68 GB of GPU memory, which starts at roughly $346 a month on the cheapest rental that fits.

Open weights · Llama 4 Community License

Llama 4 Scout

A 109B MoE with 17B active parameters across 16 experts that fits on a single H100 with INT4 quantization.

Jump to: Specs Pricing Self-hosting Similar models FAQ More from Meta

Visit website Compare vs other LLMs →

Cheapest via Azure

Input: $0.16 /1M tokens
Output: $0.64 /1M tokens

5 providers

Key Specifications

Context window: 10M tokens
Knowledge cutoff: Aug 2024
Released: Apr 2025
Parameters: 109B, 17B active
Inputs: Text, image

Capabilities Show details: Function calling Connect to external tools, APIs, and systems.

Hosted API pricing

Input tokens M Output tokens M

Provider	Input /1M tokens	Output /1M tokens	Cost at 10M in + 2M out
Azure Cheapest	$0.16	$0.64	$2.88	View
Replicate	$0.17	$0.65	$3.00	View
Novita	$0.18	$0.59	$2.98	View
Cloudflare	$0.27	$0.85	$4.40	View
Meta Creator	Open weights, no hosted price			View

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

Llama 4 Scout needs about 68 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 8× RTX 3060 at about $346 a month.

That costs the same as roughly 1B tokens a month on Azure's API. Self-hosting is more expensive below that volume.

Single node ≤ 8

Precision	Memory	Cheapest fit (32K context)(Full 10.2M context)	Cost /mo	Break-even vs API
4-bitINT4 / FP4	68 GB1,069 GB	8× RTX 3060	$346$34,618	1B tokens /mo144B tokens /mo
8-bitFP8 / INT8	114 GB1,118 GB	8× RTX 4060 Ti	$634$34,618	3B tokens /mo144B tokens /mo
16-bitFP16 / BF16	226 GB2,233 GB	8× RTX A6000 –	$3,168–	13B tokens /mo–

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Similarly priced models

The models nearest Llama 4 Scout by blended rate, each at its own cheapest provider.

Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Llama 4 Scout
GPT-4o Mini OpenAI	$0.225	$0.15	$0.60	128K	Oct 2023	−6%
MiniMax-M2.7 MiniMax	$0.225	$0.15	$0.60	205K		−6%
Mistral Small 4 Mistral	$0.225	$0.15	$0.60	256K		−6%
Qwen3.8-27B Alibaba Cloud	$0.225	$0.17	$0.50	262K		−6%
Qwen3-Coder-Next Alibaba Cloud	$0.23	$0.08	$0.98	262K		−4%
Llama 4 Scout This model Meta	$0.24	$0.16	$0.64	10M	Aug 2024
Qwen3.5-122B-A10B Alibaba Cloud	$0.2533	$0.12	$0.92	262K		+6%
Llama 4 Maverick Meta	$0.2833	$0.20	$0.70	1M	Aug 2024	+18%
Qwen3-VL-30B-A3B Instruct Alibaba Cloud	$0.2833	$0.20	$0.70	262K		+18%
Muse Glimmer 30B Meta	$0.30	$0.20	$0.80	131K	Jan 2026	+25%
Qwen2.5-7B Instruct Alibaba Cloud	$0.30	$0.30	$0.30	33K		+25%

Prices are USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Salad

Access 60,000+ daily active GPUs across 191 countries, from $0.02/hour

Run RTX 50-series and 40-series cards without datacenter pricing

Pick a priority level to balance cost against interruptions

Per-second billing, with no charge for cold starts or image pulls

View Pricing

Frequently Asked Questions

What is Llama 4 Scout good for?: Text and image work over an extremely long context. Open weights under the Llama 4 Community License, servable on a single high-memory GPU.
When is Llama 4 Scout not a good fit?: Video input and structured output, which it has neither of. Memory follows the full 109B parameters, not the 17B active, so it takes more than Meta's dense 70B Llamas.
What is the cheapest way to run Llama 4 Scout?: Hosted, unless you push serious volume. Azure charges $0.16 in / $0.64 out per 1M tokens. The cheapest rental that fits is 8x RTX 3060 at $346 a month, which costs the same as about 1B tokens a month on that API.
Can I self-host Llama 4 Scout?: Yes. The weights are released under the Llama 4 Community License. At 4-bit it needs about 68 GB of GPU memory, which starts at roughly $346 a month on the cheapest rental that fits.

More from Meta

Model	Context	Cutoff	Input /1M	Output /1M
Llama 4 Maverick Open weights	1M	Aug 2024	$0.20	$0.70
Muse Glimmer 30B Open weights	131K	Jan 2026	$0.20	$0.80
Llama 3.3 70B Open weights	128K	Dec 2023	$0.13	$0.40
Llama 3.2 11B Vision Open weights	128K	Dec 2023	$0.05	$0.68
Llama 3.2 3B Open weights	128K	Dec 2023	$0.05	$0.34
Llama 3 8B Open weights	8K	Mar 2023	$0.05	$0.25
Llama 3.2 1B Open weights	128K	Dec 2023	$0.03	$0.20
Llama 3 70B Open weights	8K	Dec 2023	$0.65	$2.75