Skip to content
AnyRouter

Llama 4 Scout 17B 16E

Tools
meta/llama-4-scout-17b-16e-instruct

Vision · 131K context · Apr 2025 · 12 upstreams

Llama 4 Scout 17B 16E is Meta's open-weight multimodal mixture-of-experts model with 17B active and 109B total parameters. It takes text and image input and has a 10M-token input context. It fits on a single H100 GPU.

Needs your own keyTo use Llama 4 Scout 17B 16E, add a key from Hugging Face, OpenRouter, Vercel AI Gateway or 9 more. AnyRouter adds no fee.
context
131K
input / 1M (list)
$0.10
output / 1M (list)
$0.30
routes
12
speed, 24h
No data yet

Upstreams

12
  1. 1Hugging FaceYour keynot addedBilled to your key
  2. 2OpenRouterYour keynot addedBilled to your key
  3. 3Vercel AI GatewayYour keynot addedBilled to your key
  4. 4DeepInfraYour keynot addedBilled to your key
  5. 5NovitaAIYour keynot addedBilled to your key
  6. 6Nous ResearchYour keynot addedBilled to your key
  7. 7ZenMuxYour keynot addedBilled to your key
  8. 8AIHubMixYour keynot addedBilled to your key
  9. 9NanoGPTYour keynot addedBilled to your key
  10. 10FluenceYour keynot addedBilled to your key
  11. 11HeliconeYour keynot addedBilled to your key
  12. 12Jiekou.AIYour keynot addedBilled to your key

Benchmarks

GPQA Diamond
51.8%

Benchmark data from Epoch AI (CC-BY 4.0).

Quick start

curl
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."
    }
  ]
}'

Details

Owner
Meta
Kind
Vision
Released
Apr 2025
Context
131K
Data policy
Provider retention
Endpoint
/api/v1/chat/completions