opendunes

Tencent models

All 9 Tencent models on OpenDunes, priced in Algerian Dinars.

Models9
Understands
TextImages
Replies with
TextImages
↑14,64 – 277,58 DA/ 1M tokens
↓58,91 – 832,42 DA/ 1M tokens
Context up to1M
6 with fills your json5 with thinks first4 with uses your tools

9 models

tencent/hy4Text

This model accepts text and pictures as input and produces text as output. It can process up to 1000 pages of material at one time and generate responses up to 65 pages long. It is designed for complex, real-world productivity tasks that require planning and the use of specific tools. However, it cannot access the internet to find new information.

TextImagesText
50 % offWas 0,70 DA≈ 0,35 DAper message↑ 138,79 DA↓ 416,21 DAper 1M tokens
by TencentNov 4, 2026
Open in chat
tencent/hy-image-v3.5-previewImage

Hy Image 3.5 Preview takes a written description plus up to 20 reference pictures and returns an image up to 4K, or an edited version of a picture you supply. It can keep one subject looking the same across a series of edits, follows your description closely, and draws Chinese and English lettering inside the picture. You can edit over several rounds.

TextImagesImages
≈ 7,99 DAper image↓ 532,54 DAper 1M image tokens
by TencentOct 5, 2026
Open in chat
tencent/hy4-previewText

Hy4 preview reads and writes text, and keeps about 1,000 pages in mind at once. Tencent built it for coding assistants, long jobs that use the tools and apps you connect to it, and office-style work that needs planning and a steady thread over many steps. Pick it when the material is very long.

TextText
≈ 0,69 DAper message↑ 277,58 DA↓ 832,42 DAper 1M tokens
by TencentAug 28, 2026
Open in chat
tencent/hy3Text

Hy3 reads and writes text, and keeps about 260 pages in mind at once. You choose how hard it thinks: not at all by default, or at a low or high level for tricky maths, coding and problems with many steps. Tencent points it at coding, game development, financial analysis, document work and web page design, and says it flags missing evidence rather than inventing an answer. Hy4 preview reads about 1,000 pages at once.

TextText
≈ 0,13 DAper message↑ 43,93 DA↓ 175,74 DAper 1M tokens
by TencentJul 6, 2026
Open in chat
tencent/hy3-previewText

Hy3 preview reads and writes text, and keeps about 260 pages in mind at once. You can switch its thinking off, or set it to low or high, trading speed for depth depending on the job. Tencent builds it for long jobs with many steps and for writing code. As a preview it is for trying this line before settling on the finished Hy3, which has the same reading size.

TextText
≈ 0,16 DAper message↑ 59,91 DA↓ 199,70 DAper 1M tokens
by TencentApr 22, 2026
Open in chat
tencent/hy-mt2-30b-a3bText

Hy-MT2-30B-A3B reads text in one language and writes it back in another, working among 33 languages. You can give it a glossary of your own terms or a style to follow, and it reads about 8 pages at once. It is the largest of Tencent's three Hy-MT2 translators and the one Tencent calls its flagship.

TextText
≈ 0,074 DAper message↑ 24,63 DA↓ 98,19 DAper 1M tokens
by TencentAug 20, 2026
Open in chat
tencent/hunyuan-a13b-instructText

Hunyuan A13B Instruct reads text and writes text back, keeping about 130 pages of conversation in mind at once. Tencent built it to think a problem through step by step, and it is aimed at maths, science, coding and questions that take several turns to untangle. Use it to work through that kind of problem. For longer files, Tencent's Hy3 reads about 260 pages at once and Hy4 preview about 1,000.

TextText
≈ 0,14 DAper message↑ 46,60 DA↓ 189,72 DAper 1M tokens
by TencentJul 8, 2025
Open in chat
tencent/hy-mt2-1.8bText

The compact 1.8B member of Tencent's Hy-MT2 translation family, covering 33 language pairs plus five Chinese dialect pairs, with glossary, context, style-guide and structured-text workflows

TextText
≈ 0,044 DAper message↑ 14,64 DA↓ 58,91 DAper 1M tokens
by TencentAug 20, 2026
Open in chat
tencent/hy-mt2-7bText

The 7B member of Tencent's Hy-MT2 translation family, between the 1.8B and the flagship, covering 33 language pairs plus five Chinese dialect pairs, with glossary, context and style-guide workflows

TextText
≈ 0,074 DAper message↑ 24,63 DA↓ 98,19 DAper 1M tokens
by TencentAug 19, 2026
Open in chat