none reviewed yet · 0 benchmark observations · latest capture Nov 15, 2026
Inspect the evidenceHy-MT2-1.8B
Accepts text and produces text.
No editorial score yet — missing data is not a low score
How scoring worksNo verified rate for your workload
Adjust workloadAt a glance
9 facts- Provider
- Tencent
- Type
- API model
- Access
- OpenRouter API; availability and price can vary by routed provider.
- Context
- 8,192 tokens
- Maximum output
- 4,096 tokens
- License / weights
- Not recorded
- Input modalities
- text
- Output modalities
- text
- Pricing notes
- $0.044 input / $0.177 output per million text tokens on OpenRouter. Routing and optional usage charges can change the total.
Good to know
In its favour
- Output price in the cheapest 10% of the 288 current text models with a verified price: $0.177 per 1M tokens, read on the vendor’s page Nov 15, 2026.
Check before you rely on it
- Small context window (8,192 tokens) for long documents or large codebases.
- Short maximum reply: 4,096 tokens.
- No tool calling listed for this route; agents usually need it.
Worked out from the catalogue’s own facts and dates by the same rule for every model. Not a review, and no one pays to change it.
Example bills
| Job (tokens per task) | Per task | Per 1,000 |
|---|---|---|
| Support chatbot reply (3K in, 400 out) | $0.0002 | $0.20 |
| Quick response (4K in, 1K out) | $0.00035 | $0.35 |
Same token sizes as the cheapest-by-task pages, so you can see where this model ranks. Jobs that do not fit its context window are left out.
The practical trade-offs
Documented strengths
Not recorded. No saved strengths assessment.
Limitations to check
- No normalized editorial score or independently checked benchmark is assigned to this catalogue addition.
Evidence & conditions
- OpenRouter catalogue
openrouter.aiDate not recorded - OpenRouter catalogue
openrouter.aiDate not recorded
No comparable benchmark observations are recorded for this entry.
Source reports, measured results, and editorial assessments are separate evidence types. Source dates do not imply a new benchmark run. Capture dates are shown when recorded; otherwise we say the capture date was not recorded. Recorded dates are compared with this catalogue snapshot (Nov 15, 2026), not today’s date.
How this page is assessed
Quality claims follow how we rate (method AIS-V2).
Money never buys rank — commercial relationships cannot change rank, eligibility, evidence quality, or publication timing.
Submit or claim a listing is free and does not skip the editorial queue.