Hy-MT2-1.8B vs text-embedding-ada-002.
model vs model · prices as of
text-embedding-ada-002 takes 2 of 5 rounds against Hy-MT2-1.8B. It is also the cheaper of the two to run, at $0.30 per million tokens against $0.31.
Hy-MT2-1.8B
$0.31/M tokens
Tencent list price, nothing below it is accounted for · $0.037 per 1,000 pages
8k context · open weights
text-embedding-ada-002
$0.30/M tokens
OpenAI list price, nothing below it is accounted for · $0.06 per 1,000 pages
8k context
List price in (lower wins)
$0.04/M
$0.10/M
List price out (lower wins)
$0.18/M
$0/M
Cheapest we can explain (lower wins)
none below list
none below list
Standard price (lower wins)
$0.31/M
$0.30/M
Cost per 1,000 pages (lower wins)
$0.037
$0.06
Context
8k tokens
8k tokens
Open weights
yes
no
Tool calling
no
no
Structured output
no
not stated
Reads images
no
no
Reasoning
no
no
Released
20 Aug 2026
15 Dec 2022
Providers selling it
3
7
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 · 0
No provider we read sells both, so running the two means two accounts.
Go further
Add a third or fourth model, or switch the weighting, in the tool.
What moved in the last seven days
- text-embedding-ada-002
Nous Portal$0.08 / $0 $0.10 / $025% dearer ·
Frequently asked
- Which is cheaper, Hy-MT2-1.8B or text-embedding-ada-002?
- text-embedding-ada-002, at $0.30 per million tokens against $0.31 for Hy-MT2-1.8B, three parts input to one part output, read on 16 Sept 2026.
- Where is each one cheapest?
- Hy-MT2-1.8B: nobody goes below the maker's own price with a reason we can point at, so $0.31 is the number to beat. text-embedding-ada-002: nobody goes below the maker's own price with a reason we can point at, so $0.30 is the number to beat.
- Can I buy both from one provider?
- No provider we read sells both, so running the two means two accounts and two bills.
- 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.