Tencent Models
Shenzhen-based technology company building the Hunyuan model family. Retains API prompts but does not train on them. Requesty routes to 5 Tencent models starting at $0.14 per 1M input tokens with context windows up to 1.0M tokens. One API key, OpenAI-compatible SDK, no markup.
Flagship model
deepseek-v4-proIntelligence Index
44.3
Coding Index
59.4
GPQA Diamond
88.8%
Terminal-Bench Hard
46.2%
All Tencent models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
deepseek-v4-pro | 1.0M | 393K | $1.74 | $3.48 | 🧠🔧⚡ | 59 |
deepseek-v4-flash | 1.0M | 393K | $0.14 | $0.28 | 🧠🔧⚡ | 56 |
minimax-m3 | 1.0M | 1.0M | $0.30 | $1.20 | 👁🧠⚡ | 59 |
kimi-k2.7-code | 262K | 262K | $0.95 | $4.00 | 👁🧠🔧⚡ | 61 |
glm-5.2 | 1.0M | 131K | $1.40 | $4.40 | 🧠🔧⚡ | 69 |
About Tencent on Requesty
How many Tencent models are available through Requesty?
Requesty routes to 5 Tencent models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Tencent model?
The cheapest Tencent model starts at $0.14 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Tencent pricing?
No. Requesty passes through exactly what Tencent charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Tencent models?
Tencent's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Tencent models hosted?
Tencent models are hosted in 🇨🇳 China. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI: filter by region on the Tencent rows in the models explorer.