codestral-latest vs hy4-preview
Both can be used on onomeo. Everything below comes from calls made through this site.
- codestral-latest
- 2 advantages
- hy4-preview
- 3 advantages
How to choose
codestral-latestFaster: 1.2s on averageHigher in this week's ranking: #9
hy4-previewLonger context: 1M tokensThinks before answeringNo training on conversations
codestral-latest
By Mistral AI
hy4-preview
By TencentNew this week
Where they differ
codestral-latesthy4-preview
On this site
1.2sAverage response this week3.5s
#9Place in this week's ranking#10
The model itself
256K tokensContext length1M tokens
4K tokensLongest reply64K tokens
NoThinks before answeringYes
The provider does not say.Conversations used for trainingNot used for training.
Oct 2024Knowledge cutoffNot published
29 May 2024Released28 Aug 2026
Where they match
- Availability, last 3 days97%
- Availability, this week's tests95%
- Price per replyFree
- Reads imagesNo
- 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. Free models are counted in calls; big models are charged by usage, in US dollars.
Compare next
codestral-latest against other models
hy4-preview against other models
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 Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.