Skip to content
Model Pulse

Model

Llama 4 Scout 17B Instruct

Open Llama with long-context vision for efficient multimodal agents

3 providers · 5 listingsreleased knowledge cutoff 2024-08open weights
$0.17
lowest input /M · LLM Gateway
$0.59
lowest output /M · LLM Gateway
10M
context window
131K
max output

Compare providers (sorted by listed input price)

3 providers list Llama 4 Scout 17B Instruct. The cheapest full-context option is Amazon Bedrock at $0.17/$0.66 per M. LLM Gateway lists lower but caps context at 131K.

5 listings
Cache read /MCache write /MCapabilitiesStatus
LLM Gatewayvariant
aws-bedrock/llama-4-scout-17b-instruct
$0.17$0.66——8Kno reasoningno toolsno structuredvisionApr 5, 2025
Amazon Bedrockvariant
us.meta.llama4-scout-17b-instruct-v1:0
$0.17$0.66——10Mno reasoningtoolsno structuredvisionApr 5, 2025
Amazon Bedrockvariant
meta.llama4-scout-17b-instruct-v1:0
$0.17$0.66——10Mno reasoningtoolsno structuredvisionApr 5, 2025
LLM Gatewayvariant
novita/llama-4-scout-17b-instruct
$0.18$0.59——131Kno reasoningno toolsno structuredvisionApr 5, 2025
DevPass (LLM Gateway)
llama-4-scout-17b-instruct
$0.18$0.59——131Kno reasoningno toolsno structuredvisionApr 5, 2025
1–5 of 5 listings

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M
$0.18unchanged
Best output /M
$0.59unchanged
Provider coverage
5
5 at the start · 24 snapshots

Published best prices are unchanged.

24 daily snapshots collected from Aug 21, 2026 through Sep 14, 2026. A price chart will appear after the first real move.

Price badge

Current price badge for Llama 4 Scout 17B Instruct
![Llama 4 Scout 17B Instruct price](https://www.vaanalytics.in/badge/meta/llama-4-scout-17b-instruct.svg)
https://www.vaanalytics.in/badge/meta/llama-4-scout-17b-instruct.svg

Live SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.

Recent changes

Changelog →
  • contextvia amazon-bedrock · Sep 13, 2026
    • description: Open multimodal Llama model for long-context analysis and efficient agents → Open Llama with long-context vision for efficient multimodal agents
    • context: 3.50M → 10M tokens
    • output: 16K → 8K tokens
  • contextvia amazon-bedrock · Sep 13, 2026
    • context: 3.50M → 10M tokens
    • output: 16K → 8K tokens

Weights

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.