tencent/hy-mt2-30b-a3b · Tencent
Tencent's flagship Hy-MT2 translation model: 33 language pairs and five Chinese dialect pairs with glossary and context-guided translation workflows.
Last checked Aug 28, 2026. Calculations use the listed base rates; provider-specific tiers, cache writes, batch pricing, and long-context rules may differ. Note: Translation-specialist model; small context window. Live OpenRouter route snapshot checked 28 Aug 2026. Confirm the current rate at the official provider source.
Input
$0.074
per 1M tokens
Output
$0.295
per 1M tokens
Cached input
—
not published
Context window
8.2K
max output 8.2K
Hy-MT2-30B-A3B (OpenRouter) cost calculator
What Hy-MT2-30B-A3B (OpenRouter) costs per task
| Use case | Input tokens | Output tokens | Cost / request | Monthly @ 1K req/day |
|---|---|---|---|---|
| Customer support chatbot | 3,500 | 350 | $0.000362 | $10.868 |
| RAG / search-augmented answers | 8,000 | 500 | $0.000739 | $22.185 |
| AI coding assistant | 12,000 | 2,000 | $0.001478 | $44.34 |
| Document summarization | 25,000 | 600 | $0.002027 | $60.81 |
| Agentic workflow | 40,000 | 1,500 | $0.003403 | $102.075 |
| Content generation | 800 | 1,200 | $0.000413 | $12.396 |
| Data extraction & tagging | 2,000 | 250 | $0.000222 | $6.653 |
| Translation | 5,000 | 5,500 | $0.001993 | $59.775 |
Assumes each use case's typical cacheable share of input. See full cost scenarios.
Compare with alternatives
| Model | Input /M | Output /M | Context | Chat request* |
|---|---|---|---|---|
| Hy-MT2-30B-A3B (OpenRouter) | $0.074 | $0.295 | 8.2K | $0.000532 |
| GPT-5.6 Solcompare | $5.00 | $30.00 | 1.1M | $0.035 |
| GPT-5.6 Terracompare | $2.00 | $12.00 | 1.1M | $0.014 |
| GPT-5.6 Lunacompare | $0.20 | $1.20 | 1.1M | $0.0014 |
| GPT-5.6 Cybercompare | $12.50 | $75.00 | 1.1M | $0.0875 |
| GPT-5.5 Standardcompare | $5.00 | $30.00 | 512K | $0.035 |
| GPT-5.5 Procompare | $30.00 | $180.00 | 512K | $0.21 |
| GPT-5.4 Workhorsecompare | $2.50 | $15.00 | 256K | $0.0175 |
| GPT-5.4 minicompare | $0.75 | $4.50 | 256K | $0.00525 |
*4,000 in + 800 out tokens, 50% cached input where available.
Related calculations
FAQ
Hy-MT2-30B-A3B (OpenRouter) costs $0.074 per 1M input tokens and $0.295 per 1M output tokens. Verified Aug 28, 2026 against https://openrouter.ai/api/v1/models.
Hy-MT2-30B-A3B (OpenRouter) supports a 8,192-token context window with up to 8,192 output tokens per request, tokenized with hy-mt2_bpe.
At $0.074/M input and $0.295/M output, Hy-MT2-30B-A3B (OpenRouter) sits below GPT-5.6 Sol ($5.00/M in, $30.00/M out) — see the comparison table for full-workload differences.