As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/llama-4-scout/

# Llama 4 Scout (17B-16E)

Meta, Llama 4 family. Status: legacy. Type: multimodal model. Released: 2025-04-05. Training cutoff: 2024-08.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face |  |  | https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct |
| AWS Bedrock | `meta.llama4-scout-17b-instruct-v1:0` |  | https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.html |
| OpenRouter | `meta-llama/llama-4-scout` |  | https://openrouter.ai/meta-llama/llama-4-scout |
| Web app |  |  | https://meta.ai |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: text, image
- Output: text
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: llama4-community

## What it has not seen

- Published training cutoff: 2024-08 (August 2024).
- AI events after it on Post-Cutoff: 2,056 (487 major, 97 historic), as of 2026-11-13.
- Already missing at launch: 29.
- Briefings of the news since August 2024: https://postcutoff.com/briefings/cutoff-2024-08-s.md (short), https://postcutoff.com/briefings/cutoff-2024-08-m.md (medium), https://postcutoff.com/briefings/cutoff-2024-08.md (full).
- Its card, with five things it has never heard of: https://postcutoff.com/you/llama-4-scout/

## What stands out

- 10M-token context (claimed) (first): Meta advertised an 'industry-leading' 10M-token context via the iRoPE architecture; hosted providers typically serve far less (e.g. ~1.3M on OpenRouter). Source: https://ai.meta.com/blog/llama-4-multimodal-intelligence/
- Single-H100 multimodal MoE: 17B active / 16 experts / 109B total; fits one H100 with Int4 quantization. Source: https://ai.meta.com/blog/llama-4-multimodal-intelligence/

## Notes

Context: 10M per Meta; provider limits vary (not listed as context_window). Knowledge cutoff Aug 2024 per Meta model card (not re-verified today). No first-party pricing verified.

Small open-weight multimodal MoE for long-context and on-prem use.

```bash
curl https://openrouter.ai/api/v1/chat/completions -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" \
 -d '{"model":"meta-llama/llama-4-scout","messages":[{"role":"user","content":"Hello"}]}'
```

Sources: https://ai.meta.com/blog/llama-4-multimodal-intelligence/ , https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct

Model page: https://postcutoff.com/m/llama-4-scout/