onomeoonomeoBeta

hy4-preview vs llama-4-scout

hy4-preview
2 advantages
llama-4-scout
1 advantage

How to choose

hy4-previewLonger context: 1M tokensThinks before answering
llama-4-scoutReads images

hy4-preview

By Tencent

llama-4-scout

By MetaNew in the last two weeks

Where they differ

hy4-previewllama-4-scout
On this site
—Availability, last 3 days91%204 calls
—Availability, this week's tests91%305 tests
—Average response this week4.9s
$3.75Reference price per million output tokensFree
UnrankedPlace in this week's ranking#10
$1.25Reference price per million input tokensFree
The model itself
1M tokensContext length320K tokens
64K tokensLongest reply16K tokens
NoReads imagesYes
YesThinks before answeringNo
Used to train and improve the provider’s models.Conversations used for trainingThe provider does not say.
Not publishedKnowledge cutoffAug 2024
28 Aug 2026Released5 Apr 2025
$0.063Reference price per million cache-read tokensFree

Where they match

  • Calls toolsYes
  • Open weightsYes

Availability over 3 days counts every call made through the site; this week's availability counts every call over the last 7 days, scheduled tests included, and response time comes from the site's own scheduled tests. Models marked as free are counted in calls; paid models are charged by usage, in US dollars.

Compare next

Figures come from real calls made through this site. Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.