uttapen

Hy4 preview vs Hy3 preview

Both sit behind the same key and the same code on uttapen — the only thing that changes is the model string, so you can run each of them against your own workload without touching anything else. On cost, Hy3 preview comes out about 4.3× cheaper.

FeatureHy4 previewHy3 preview
ProviderTencentTencent
Model idtencent/hy4-previewtencent/hy3-preview
Context1,048,576 tokens262,144 tokens
Max output64,000 tokens235,929 tokens
Input / 1M tokens241,964 toman52,223 toman
Output / 1M tokens725,603 toman174,075 toman
≈ one 1,000-word request1,258 toman294 toman
Input caching12,185 toman / 1M17,408 toman / 1M
Image inputNoNo
File inputNoNo
Tool callingYesYes
JSON outputYesNo
Reasoning modeYesYes

Which one for what?

Hy4 preview

  • Multi-step problems, maths, and tracking down a bug
  • Whole documents or a codebase in a single request
  • Agents that call your own APIs and database
1,258 toman per 1,000 words · Model page

Hy3 preview

  • Multi-step problems, maths, and tracking down a bug
  • Whole documents or a codebase in a single request
  • Agents that call your own APIs and database
  • High-volume work where cost per call decides
294 toman per 1,000 words · Model page

Run both with the same code

Swap the model value between the two ids and send the same request twice; what each answer cost comes back in the X-Uttapen-Cost-Toman header.

curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tencent/hy4-preview",
    "messages": [{"role": "user", "content": "Introduce yourself in one sentence."}],
    "stream": true
  }'

model = "tencent/hy3-preview"

More comparisons: all pairs · model rankings · full catalogue

base_url = https://api.uttapen.ir/v1