Conversation / Quote
Kinfra-Text-Embedding-4b API Price
Tencent Cloud TokenHub · Kinfra-Text-Embedding-4b
Input · Cache Miss
¥0.6 /1M tokens
Output
¥0 /1M tokens
Cache Hit Input
— /1M tokens
| Billing | CNY · 1M tokens |
|---|---|
| Modalities | Text |
| Deep Thinking | — |
| Verified Date | 2026-10-09 |
| Official pricing page | cloud.tencent.com/document/product/1823/130055 ↗ |
Source text: the note below is the model's official text, kept in its original Chinese and not translated.
向量模型，计费项为文本输入
Report a pricing issue
Found inaccurate pricing or model information? We will review it.
Tencent Cloud TokenHub Related Models
- Hy4 Preview ¥6 / ¥18
- Hy3 ¥1 / ¥4
- Hy-MT2-Pro ¥0.5 / ¥2
- Hy-MT2-Plus ¥0.5 / ¥2
- Hy-MT2-Lite ¥0.3 / ¥1.2
- Hy-Role-Latest ¥2.4 / ¥9.6
- Hy-Role ¥2.4 / ¥9.6
- HY-Vision-2.0-Instruct ¥7.5 / ¥17.5
- HY-Vision-1.5-Thinking ¥3 / ¥9
- HY-Vision-Video ¥3 / ¥9
- YT-VITA ¥1.2 / ¥3.5
- Wand-Vega-Image-Lite ¥0.135 /image
- Wand-Vega-Image-Flash ¥0.45 /image
- Wand-Vega-Image-Pro ¥0.95 /image
- Hy-Image-3.5-preview ¥0.15 /image
- Hy-Image-3.0 Tiered
- HY-Video-1.5 ¥0.3 /sec
- WAND-Vega-Video-1.0-Lite ¥0.375 /sec
- YT-Video-2.0 ¥2 /call
- YT-Video-HumanActor ¥1 /sec
- WAND-Dubbing-Clone-V1 ¥0.1228 /sec
- WAND-Dubbing-Clone-V2 ¥0.2061 /sec
- WAND-Dubbing-STS-v1 Tiered
- Hy-ASR-3.0-Preview Tiered
- WAND-ASR-V1 Tiered
- HY-World-2.1 Panorama ¥5 /unit
- HY-World-2.1 3D Scene ¥80 /unit
- HY-3D-3.1 ¥1.8 /call
- Hy3 ¥1 / ¥4
- Hy-MT2-Pro ¥0.5 / ¥2
- Hy-MT2-Plus ¥0.5 / ¥2
- Hy-MT2-Lite ¥0.3 / ¥1.2
- Hy-Role-Latest ¥2.4 / ¥9.6
- Hy-Role ¥2.4 / ¥9.6
- DeepSeek-V4-Flash ¥1 / ¥2
- DeepSeek-V4-Pro ¥12 / ¥24
- GLM-5.3 ¥8 / ¥28
- GLM-5.3-Flash ¥0.8 / ¥2.8
- GLM-5.3-FlashX ¥2 / ¥7
- GLM-5.2 ¥8 / ¥28
- GLM-5.1 ¥6 /1M tokens
- GLM-5V-Turbo ¥5 /1M tokens
- GLM-5-Turbo ¥5 /1M tokens
- GLM-5 ¥4 /1M tokens
- Kimi-K2.6 ¥6.5 / ¥27
- MiniMax-M3 ¥2.1 /1M tokens
- MiniMax-M2.7 ¥2.1 / ¥8.4
- Qwen3.5-Flash ¥0.2 /1M tokens
- Qwen3.5-Plus ¥0.8 /1M tokens
- MiMo-V2.6-Pro ¥3 / ¥6
- MiMo-V2.6-Flash ¥1 / ¥2
- MiMo-V2.5-Pro ¥3 / ¥6
- YT-VITA ¥1.2 / ¥3.5
- HY-Vision-2.0-Instruct ¥7.5 / ¥17.5
- HY-Vision-1.5-Thinking ¥3 / ¥9
- HY-Vision-Video ¥3 / ¥9
- Kinfra-Text-Embedding-0.6b Tiered
- Kinfra-VL-Embedding-2b ¥0.5 /1M tokens
- Kinfra-VL-Embedding-8b ¥0.6 /1M tokens
- WAND-Vega-Image-1.0-Lite ¥0.135 /image
- WAND-Vega-Image-1.0-Flash ¥0.45 /image
- WAND-Vega-Image-1.0-Pro ¥0.95 /image
- Kling-Image-v3 Tiered
- Kling-Image-o1 Tiered
- Kling-Image-v3-omni ¥0.2 /image
- Seedream-Image-v5.0-pro ¥0.3 /image
- Seedream-Image-v5.0-lite Tiered
- Vidu-Image-q2 ¥0.1875 /image
- HY-Image-V3.0 Tiered
- HY-Image-Lite Tiered
- Hy-Video-1.5 Tiered
- MiniMax-Video-H3-Max ¥0.33 /sec
- MiniMax-Video-H3 ¥0.5 /sec
- MiniMax-Video-v2.3 ¥0.3333 /sec
- MiniMax-Video-v2.3-fast ¥0.225 /sec
- Vidu-Video-q3.0-pro ¥0.2813 /sec
- Vidu-Video-q3.0-turbo ¥0.125 /sec
- Vidu-Video-q3.0 ¥0.2188 /sec
- Vidu-Video-q2.0-pro ¥0.625 /sec
- Vidu-Video-q2.0-turbo ¥0.1875 /sec
- Vidu-Video-q2.0 ¥0.3125 /sec
- Kling-Video-motion-control-v2.6 ¥0.5 /sec
- Kling-Video-motion-control-v3.0 ¥0.9 /sec
- Kling-Video-V3 ¥0.9 /sec
- Kling-Video-v3-turbo ¥0.8 /sec
- Kling-Video-v3-omni ¥0.8 /sec
- Kling-Video-V2.6 ¥0.5 /sec
- Kling-Video-V2.5-turbo ¥0.3 /sec
- Kling-Video-o1 ¥0.6 /sec
- PixVerse-Video-v6 ¥0.2053 /sec
- PixVerse-Video-v5.6 ¥0.4693 /sec
- PixVerse-Video-c1 ¥0.2346 /sec
- HY-World-2.1-panorama Tiered
- HY-World-2.1-scene Tiered
- Tripo-3D-Rigging-Check Free
- MiniMax-Music-v3.0 Tiered
- MiniMax-Music-v2.6 Tiered
- MiniMax-Music-v2.5 Tiered
- MiniMax-Music-v2.0 Tiered
- Mureka-Music-v9 Tiered
- IndexTTS-2 Tiered
- MiniMax-Speech-2.8-HD Tiered
- MiniMax-Speech-2.8-Turbo Tiered
- MiniMax-Speech-2.6-HD Tiered
- MiniMax-Speech-2.6-Turbo Tiered
- MiniMax-Speech-02-HD Tiered
- MiniMax-Speech-02-Turbo Tiered
- MiniMax-Voice-Clone Tiered
- MiniMax-Voice-Design Tiered
FAQ
How much does the Kinfra-Text-Embedding-4b API cost?
Input ¥0.6/1M tokens, output ¥0/1M tokens
Which input modalities does Kinfra-Text-Embedding-4b support?
Text.
How does Kinfra-Text-Embedding-4b compare with peers on value?
Tencent Cloud TokenHub Kinfra-Text-Embedding-4b is priced low among comparable models; compare against GPT-4o, Claude 3.5 and Gemini 2.5. See the Pricemon market table for a full comparison.
What use cases suit Kinfra-Text-Embedding-4b?
Good for: chat systems, customer support, content generation, coding assistance, data analysis.
Does Kinfra-Text-Embedding-4b have a free tier?
Check Tencent Cloud TokenHub's official pricing page for the latest free quota, trial policy and tiered pricing. Policies differ by vendor and change over time.