Llama 4 Scout 17B Instruct pricing & specs

Meta · released 2025-04-05 · ● verified 2026-10-11

input / 1M$0.18via Novita AI
output / 1M$0.59via Novita AI
context131.1K
max output131.1K

// price history ($/1M tokens)

$0.6785
input $/1Moutput $/1M2025-04-05 → 2026-10-11

// cheaper or similar alternatives

modelinoutctxvs Llama 4 Scout 17B Instruct
Gemma 4 E2B IT$0.04$0.08131.1K−82.3%
Qwen3.7 Flash$0.03$0.131M−80.5%
Gemma 3 12B IT$0.05$0.10131.1K−77.9%
Gemma 3 27B IT$0.08$0.16131.1K−64.6%
Ministral 3 3B$0.10$0.10131.1K−64.6%

// price by host

hostin $/1Mout $/1M
Novita AI$0.18$0.59
Amazon Bedrock$0.17$0.66
Google Vertex AI$0.25$0.70
Cloudflare Workers AI$0.27$0.85

// faq

How much does Llama 4 Scout 17B Instruct cost?

Llama 4 Scout 17B Instruct costs $0.18 per million input tokens and $0.59 per million output tokens (cheapest tracked host: Novita AI). At 50M input and 10M output tokens per month that is about $14.90.

What is the context window of Llama 4 Scout 17B Instruct?

131.1K tokens, with up to 131.1K output tokens per request.

What are cheaper alternatives to Llama 4 Scout 17B Instruct?

Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), Gemma 3 12B IT ($0.05 in / $0.10 out) offer the same input types and capabilities for less.

Is Llama 4 Scout 17B Instruct open weights?

Yes. It is available from 4 tracked hosts; the cheapest is Novita AI at $0.18 input and $0.59 output per million tokens.

// spec sheet

input / 1M
$0.18
output / 1M
$0.59
blended (3:1)
$0.2825
context
131.1K
max output
131.1K
input types
text · image
reasoning
no
tool calling
yes
structured output
no
open weights
yes
knowledge cutoff
2024-08
price source
Novita AI

report a data error

// cost calculator

modelin $/1Mout $/1M= monthly
Gemma 4 E2B IT$0.04$0.08$2.80
Qwen3.7 Flash$0.03$0.13$2.80
Gemma 3 12B IT$0.05$0.10$3.50
Llama 4 Scout 17B Instruct$0.18$0.59$14.90

Base-tier list prices. Long-context tiers, caching and batch discounts are not included.