Hy-MT2-30B-A3B vs Hy-MT2-7B.
model vs model · prices as of
Hy-MT2-30B-A3B and Hy-MT2-7B split the 5 rounds this table counts: the two list price rows, the cheapest price we can explain, the standard price and context. The weighting you pick decides the rest.
TencentHy-MT2-30B-A3B
$0.52/M tokens
Tencent list price, nothing below it is accounted for · $0.0621 per 1,000 pages
8k context · open weights
TencentHy-MT2-7B
$0.52/M tokens
Tencent list price, nothing below it is accounted for · $0.0621 per 1,000 pages
8k context · open weights
List price in (lower wins)
$0.07/M
$0.07/M
List price out (lower wins)
$0.29/M
$0.29/M
Cheapest we can explain (lower wins)
none below list
none below list
Standard price (lower wins)
$0.52/M
$0.52/M
Cost per 1,000 pages (lower wins)
$0.0621
$0.0621
Context
8k tokens
8k tokens
Open weights
yes
yes
Tool calling
no
no
Structured output
yes
yes
Reads images
no
no
Reasoning
no
no
Released
20 Aug 2026
19 Aug 2026
Providers selling it
3
3
Price we measure against
the maker's own
the maker's own
Trains on your prompts (no is better)
no provider to check
no provider to check
Providers selling both · 3
Kilo Gateway$0.52 / $0.52
OpenRouter$0.52 / $0.52- Tencent$0.52 / $0.52
Hy-MT2-30B-A3B then Hy-MT2-7B, per million tokens
Go further
Add a third or fourth model, or switch the weighting, in the tool.
Frequently asked
- Which is cheaper, Hy-MT2-30B-A3B or Hy-MT2-7B?
- Neither: both run at $0.52 per million tokens, three parts input to one part output, read on 16 Sept 2026.
- Where is each one cheapest?
- Hy-MT2-30B-A3B: nobody goes below the maker's own price with a reason we can point at, so $0.52 is the number to beat. Hy-MT2-7B: nobody goes below the maker's own price with a reason we can point at, so $0.52 is the number to beat.
- Can I buy both from one provider?
- Yes. 3 providers sell both: Kilo Gateway, OpenRouter, Tencent. The cheapest of them for the two together is Kilo Gateway.
- Which holds more context?
- Both hold 8k tokens in one call.
Prices exclude tax and are per million tokens, read 16 Sept 2026 from each provider's own catalog. The standard price blends three parts input to one part output; a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.