Tencent API pricing
Live API prices for every Tencent model SF·SIX tracks: per 1M tokens at the standard tier from the cheapest provider, or per image, second or character in the provider’s own unit.
Tencent has 18 models with live API prices on SF·SIX, 7 models priced per 1M tokens and 11 models in native units (per image, second or character). The cheapest is Hy-MT2-1.8B at $0.044 per 1M input and $0.177 per 1M output tokens, via Tencent (fp8). The most used on OpenRouter is Hy4 preview (1.24T tokens on 2026-10-16).
- Models with live prices
- 18 (7 per token, 11 per native unit)
- Cheapest language model
- Hy-MT2-1.8B$0.044 / $0.177 per 1M tokens
- Most used on OpenRouter (2026-10-16)
- Hy4 preview1.24T tokens
- Newest model
- Hy4 preview2026-08-28
- Providers serving these models
- 8
Tencent token prices (USD per 1M tokens)
| Model | Input / 1M | Output / 1M | Blended 3:1 | Cheapest standard provider | Providers | Context (tokens) | OpenRouter tokens / day |
|---|---|---|---|---|---|---|---|
| Hy3 | $0.132 | $0.528 | $0.231 | Tencentfp8 | 5 | 262,144 | 477.68B |
| Hy4 preview | $0.834 | $2.50 | $1.25 | Tencentfp8 | 4 | 1,048,576 | 1.24T |
| Hy-MT2-1.8B | $0.044 | $0.177 | $0.0773 | Tencentfp8 | 1 | 8,192 | Not in named rows |
| Hy-MT2-30B-A3B | $0.074 | $0.295 | $0.1292 | Tencentfp8 | 1 | 8,192 | Not in named rows |
| Hy-MT2-7B | $0.074 | $0.295 | $0.1292 | Tencentfp8 | 1 | 8,192 | Not in named rows |
| Hy3 preview | $0.18 | $0.60 | $0.285 | GMI Cloudbf16 | 1 | 262,144 | Not in named rows |
| Hunyuan A13B Instruct | $0.14 | $0.57 | $0.2475 | SiliconFlowfp8 | 1 | 131,072 | Not in named rows |
Each model’s headline price: the cheapest qualifying provider at the standard tier in the default region. Most widely served first.
Tencent prices in native units
| Model | Price | Billing unit | Provider |
|---|---|---|---|
| Hunyuan3d V3 (text-to-3d) | $0.015 | unit | fal |
| Hunyuan3d V3 (sketch-to-3d) | $0.015 | unit | fal |
| Hunyuan3d V3 (image-to-3d) | $0.015 | unit | fal |
| Hunyuan Image (v3 / text-to-image) | $0.10 | megapixel | fal |
| Hunyuan Image (v2.1 / text-to-image) | $0.10 | megapixel | fal |
| Hunyuan3D | $0.16 | generation | fal |
| Hunyuan3D (mini / turbo) | $0.08 | generation | fal |
| Hunyuan3D (mini) | $0.10 | generation | fal |
| Hunyuan3D (multi-view / turbo) | $0.14 | generation | fal |
| Hunyuan3D (multi-view) | $0.16 | generation | fal |
| Hunyuan3D (turbo) | $0.14 | generation | fal |
Image, video, audio and other endpoints priced in the provider’s own unit; never converted with assumptions. Most widely served first.
Method
Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Missing prices are unknown, not free. OpenRouter tokens per day are the latest full UTC day of OpenRouter’s public rankings (named rows only). Prices move: see AI API price changes for recent cuts and increases.