Llama-4-Scout-17B-16E-Instruct vs Saba

API pricing, benchmark indices and specs — updated 19 October 2026.

meta-llama · A · Open weights

Params

108.6 B

Context

—

30d

145 K

mistralai · B · API-only

Input / 1M

$0.20

Output / 1M

$0.60

AA index

6.5

proprietary · 32.8K context

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Llama-4-Scout-17B-16E-Instruct	Saba
Deployment	Open weights · also via API	API-only (closed weights)
Parameters	108.6 B	n/a — API-only
Architecture	Llama4ForConditionalGeneration	n/a — API-only
Context length	327,680	32,768
Licence	other	Proprietary
Commercial use	Unknown	Per API terms
Languages	12	n/a — API-only
Downloads 30d	144,941	n/a — API-only
Downloads all time	7.8 M	n/a — API-only
Quantizations on the Hub	SAFETENSORS	n/a — API-only
Gated	Yes — accept licence	n/a — API-only
First seen on the Hub	2025-04-02	n/a — API-only
API input price / 1M tokens	$0.10	$0.20
API output price / 1M tokens	$0.30	$0.60
Est. cost per 1M input + 1M output tokens	$0.40	$0.80
Cached input / 1M tokens	—	$0.02
AA Intelligence Index	6.5	6.5
AA Coding Index	8.2	—
AA Agentic Index	0.5	—
Max output tokens	16,384	26,214
API providers	2	1
Tool calling	Yes	Yes
Reasoning mode	No	No

Estimated cost of 1M input + 1M output tokens via OpenRouter

Llama-4-Scout-17B-16E-Instruct $0.40

Saba $0.80

Llama-4-Scout-17B-16E-Instruct is 2.0× cheaper at list price.

On RTX 4090 · 24 GB · 8K context unless noted

Llama-4-Scout-17B-16E-Instruct · fp16 255.8 GB / 24 GB

❌ Won’t fit