hy4-previewTencent
- api
- chat
- hosting
- China
- model lab
- Tencent
- weights
- open
- added
- August 2026
- model id
- tencent/hy4-preview
capabilities 4/8
- input
- $0.83
- output
- $2.50
- cache write
- -
- cache read
- $0.04
worked cost
| volume | cost |
|---|---|
| 100K in + 10K out | $0.11 |
| 1M in + 100K out | $1.08 |
| 10M in + 1M out | $10.84 |
Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing
no measured traffic for this endpoint yet. pricing above is the provider's own
no published scores for this exact variant. region deployments and highspeed tiers usually share the base model's results
- retention
- none
- trains on prompts
- no
- hosted in
- China
Terms are the provider's, not Requesty's: routing a request here puts it under them. Tencent Cloud Privacy Policy
Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.
tencent/hy4-previewthis id pins the tencent deployment, with no routing and no failover. the managed id on the canonical page routes across all 1 providers instead
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="tencent/hy4-preview", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models
Hy4 preview is Tencent's flagship class MoE model with 770B total parameters and 49B activated, supporting a 1M token context window. It is optimized for agent, coding, and productivity scenarios, with strong task decomposition, context tracking, instruction following, and long chain execution. It is suited for coding agents, complex tool use, and multi step agentic workflows.
questions 5
How much does hy4-preview cost?
What is the context window of hy4-preview?
What can hy4-preview do?
How do I use hy4-preview with the OpenAI SDK?
Can I run hy4-preview through Requesty?
more from tencent 8
| endpoint | ctx | in /M |
|---|---|---|
| mimo-v2.6-flash | 1.0M | $0.14 |
| mimo-v2.6-pro | 1.0M | $0.43 |
| glm-5.3-flashx | 1.0M | $0.37 |
| deepseek-v4.1-flash | 1.0M | $0.30 |
| glm-5.3-flash | 1.0M | $0.15 |
| glm-5.3 | 1.0M | $1.40 |
| kimi-k3 | 1.0M | $3.00 |
| hy3 | 262K | $0.13 |
call hy4-preview through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology