# Llama 4 Scout 17B 16E

> Meta's Llama 4 Scout with 17B parameters and 16 experts, featuring native multimodal support with 10M context window via interleaved attention.

**ID**: `meta/llama-4-scout-17b-16e-instruct`  
**Creator**: meta  
**Category**: text  
**Context**: 131K tokens  
**Pricing**: $0.10 / $0.30 per 1M · billed by your provider (BYOK)  
**Released**: 2025-04-05  
**Web page**: https://anyrouter.dev/model/meta/llama-4-scout-17b-16e-instruct

**Input modalities**: text, image  
**Output modalities**: text  

**Tokenizer**: Llama

**Capabilities**: chat, reasoning, function-calling, vision, streaming

**Aliases**: `meta-llama/llama-4-scout-17b-16e-instruct`

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "meta/llama-4-scout-17b-16e-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| huggingface-byok | $0.27/M (list) | $0.85/M (list) |
| openrouter-byok | $0.10/M (list) | $0.30/M (list) |
| vercel-byok | $0.17/M (list) | $0.66/M (list) |
| deepinfra-byok | $0.10/M (list) | $0.30/M (list) |
| novita-byok | $0.18/M (list) | $0.59/M (list) |
| nousresearch-byok | $0.10/M (list) | $0.30/M (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Benchmarks

- **GPQA Diamond**: 0.5
- **SciCode**: 0.2
- **MATH Level 5**: 0.6
- **OTIS Mock AIME**: 0.1

Benchmark data from [Epoch AI](https://epoch.ai/benchmarks) (CC-BY 4.0).

## Model card

- Architecture: mixture of experts [2]
- Total parameters: 109B [1,2]
- Active parameters: 17B [1,2]
- Native context: 10000000 tokens [1,2]
- Training cutoff: 2024-08 [1]
- License: Llama 4 Community License Agreement, open weights (https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct) [1]

### Strengths [2,1]

- Native text and image input with early fusion
- 10M-token input context
- Fits on a single H100 GPU

### Known limits [1]

- Can give inaccurate or objectionable answers
- Vendor testing did not cover all scenarios; run your own safety tests

### Use cases [1]

- Assistant-style chat
- Visual reasoning
- Image captioning and question answering

### Links

- announcement: https://ai.meta.com/blog/llama-4-multimodal-intelligence/
- model card: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct
- docs: https://www.llama.com/models/llama-4/

### Sources

1. [meta-llama/Llama-4-Scout-17B-16E-Instruct](https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct) (accessed 2026-10-14)
2. [The Llama 4 herd](https://ai.meta.com/blog/llama-4-multimodal-intelligence/) (accessed 2026-10-14)

## Source

- Upstream docs: https://developers.cloudflare.com/workers-ai/models/llama-4-scout-17b-16e-instruct/