# Llama 4 70B vs Llama 4 Scout

Llama 4 70B is not currently in the Allocate serving catalog, so this page lists no prices for it: every price on this site comes from the live catalog.

## Specifications

| | Llama 4 70B | Llama 4 Scout |
| --- | --- | --- |
| Lab | Meta | Meta |
| Access | Not served on Allocate | Open weights |
| Context window | n/a | 1M tokens |
| List price, input | Not served | $0.18 / M tokens |
| List price, output | Not served | $0.59 / M tokens |
| Cached input | n/a | n/a |
| License | Not listed | Llama community |
| Fine-tunable | Yes | Yes |

Specifications and provider list prices from the Allocate catalog, checked 2026-07-08. Billed price is list plus the 7% transaction fee.

## Choose Llama 4 70B for

- First private fine-tunes
- Classification and extraction
- On-boundary deployments

## Choose Llama 4 Scout for

- Whole-document reasoning
- High-volume extraction
- Fine-tuning under the Llama 4 license

## Common questions

### Which has the bigger context window?

Llama 4 Scout: 1,048,576 tokens (1M) against an unlisted window for Llama 4 70B.

### Can I fine-tune Llama 4 70B or Llama 4 Scout?

Both publish open weights (Llama 4 70B: Not listed; Llama 4 Scout: Llama community), so both can be fine-tuned. On Allocate the trained weights stay inside your boundary and belong to you.

---

[HTML page](https://allocate.network/compare/llama-4-70b-vs-meta-llama-4-scout-17b-16e-instruct) · [Llama 4 70B](https://allocate.network/models/llama-4-70b.md) · [Llama 4 Scout](https://allocate.network/models/meta-llama-4-scout-17b-16e-instruct.md) · [Machine-readable catalog](https://allocate.network/catalog.json)