Tencentopen weightsHy-MT2-1.8B pricing
$0.044 per 1M input tokens and $0.18 per 1M output tokens. In real work that is 0.03¢ per chat answer and 0.10¢ to summarize a 20-page PDF.
What Hy-MT2-1.8B costs per task
Token counts estimated from a measured model of the same lab (Qwen3.8 Flash), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.03¢$0.29 / 1,000 | 88 in · 689 out · 909 reasoning | 26 of 336 | estimated |
| Reply to a customer email | 0.01¢$0.14 / 1,000 | 326 in · 98 out · 587 reasoning | 34 of 336 | estimated |
| Write a 1,500-word blog post | ≥0.28¢$2.84 / 1,000 | 104 in · 0 out · 16,000 reasoning | 83 of 336 | estimated |
| Write 10 product descriptions | ≥0.28¢$2.85 / 1,000 | 345 in · 0 out · 16,000 reasoning | 101 of 336 | estimated |
| Translate 1,000 words | 0.03¢$0.29 / 1,000 | 1,386 in · 1,166 out · 136 reasoning | 16 of 336 | estimated |
| Proofread one page (500 words) | 0.04¢$0.36 / 1,000 | 777 in · 671 out · 1,159 reasoning | 29 of 336 | estimated |
| Summarize a 20-page PDF | 0.10¢$1.04 / 1,000 | 13,119 in · 501 out · 2,141 reasoning | 22 of 336 | estimated |
| Extract data from an invoice | 0.04¢$0.41 / 1,000 | 501 in · 561 out · 1,617 reasoning | 38 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥0.31¢$3.11 / 1,000 | 6,357 in · 0 out · 16,000 reasoning | 34 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.07¢$0.68 / 1,000 | 3,751 in · 974 out · 1,912 reasoning | 27 of 336 | estimated |
| Classify 100 support tickets | 0.16¢$1.55 / 1,000 | 1,463 in · 534 out · 7,879 reasoning | 52 of 336 | estimated |
| Review 500 lines of code | ≥0.30¢$3.05 / 1,000 | 4,874 in · 0 out · 16,000 reasoning | 35 of 336 | estimated |
| Write a SQL query | 0.05¢$0.47 / 1,000 | 177 in · 405 out · 2,225 reasoning | 38 of 336 | estimated |
| Run a 50-step coding agent | 12¢$116 / 1,000 | 2,259,875 in · 15,150 out · 80,850 reasoning | 66 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Hy-MT2-1.8B through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
| T Tencentfp8 | $0.044 / $0.18 | - | 8K |
Price history
First seen in our price history on Aug 21, 2026 at $0.044 input / $0.18 output. The list price has not changed since.
FAQ
How much does Hy-MT2-1.8B cost?
Hy-MT2-1.8B costs $0.044 per 1 million input tokens and $0.18 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.03¢ and summarizing a 20-page PDF about 0.10¢.
Where is Hy-MT2-1.8B cheapest?
Among 1 providers we track, the lowest list price today is at Tencent: $0.044 input and $0.18 output per 1M tokens.
Is the Hy-MT2-1.8B cost per task measured or estimated?
Estimated: Hy-MT2-1.8B was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of Tencent. Real usage can differ.