Conversation / Quote
Embedding-2 API Price
Zhipu BigModel · Embedding-2
| Billing | CNY · 1M tokens |
|---|---|
| Context Window | 8K tokens |
| Modalities | Text |
| Deep Thinking | — |
| Batch API | 50% off (input ¥0.25 / output ¥NaN) |
| Verified Date | 2026-10-13 |
| Official pricing page | docs.bigmodel.cn/cn/guide/start/pricing ↗ |
Source text: the note below is the model's official text, kept in its original Chinese and not translated.
Batch API 定价 0.25 元/百万 Tokens
Report a pricing issue
Found inaccurate pricing or model information? We will review it.
Zhipu BigModel Related Models
- GLM-5.3 ¥8 / ¥28
- GLM-5.3-Flash ¥0.8 / ¥2.8
- GLM-5.3-FlashX ¥2 / ¥7
- GLM-5.1 ¥6 / ¥24
- GLM-5.2 ¥8 / ¥28
- GLM-5 ¥4 / ¥18
- GLM-5-Turbo ¥5 / ¥22
- GLM-5V-Turbo ¥5 / ¥22
- GLM-OCR ¥0.2 / ¥0.2
- GLM-4.6V ¥1 / ¥3
- GLM-Image Tiered
- CogVideoX-3 Tiered
- GLM-TTS Tiered
- GLM-ASR-2512 ¥16 / ¥0
- GLM-4.7 ¥2 / ¥8
- GLM-4.5-Air ¥0.8 / ¥2
- GLM-4.7-FlashX ¥0.5 / ¥3
- GLM-4.7-Flash Free
- GLM-4-Plus ¥5 / ¥5
- GLM-4-Air-250414 ¥0.5 / ¥0.5
- GLM-4-AirX ¥10 / ¥10
- GLM-4-Long ¥1 / ¥1
- GLM-4-Assistant ¥5 / ¥5
- GLM-Z1-Air ¥0.5 / ¥0.5
- GLM-Z1-AirX ¥5 / ¥5
- GLM-Z1-FlashX ¥0.1 / ¥0.1
- GLM-4-FlashX-250414 ¥0.1 / ¥0.1
- GLM-4-Flash-250414 Free
- GLM-Z1-Flash Free
- GLM-4.6V-FlashX ¥0.15 / ¥1.5
- GLM-4.6V-Flash Free
- GLM-4.5V ¥2 / ¥6
- GLM-4V-Plus-0111 ¥4 / ¥4
- GLM-4V-Flash Free
- GLM-4.1V-Thinking-FlashX ¥2 / ¥2
- GLM-4.1V-Thinking-Flash Free
- CogView-4 Tiered
- CogVideoX-2 Tiered
- ViduQ1-Text ¥2.5 /call
- ViduQ1-Image ¥2.5 /call
- ViduQ1-Start-End ¥2.5 /call
- Vidu2-Image ¥1.25 /call
- Vidu2-Start-End ¥1.25 /call
- Vidu2-Reference ¥2.5 /call
- CogView-3-Flash Free
- CogVideoX-Flash Free
- GLM-TTS-Clone Tiered
- GLM-4-Voice Tiered
- GLM-Realtime-Flash ¥0.18 /min
- GLM-Realtime-Air ¥0.3 /min
- CodeGeeX-4 Tiered
- GLM-5.3 ¥6.9 / ¥24
- GLM-5.3-Flash ¥2.3 / ¥8
- GLM-5.3-FlashX ¥2 / ¥7
- GLM-5.2 ¥8 / ¥28
- GLM-5.1 ¥6 / ¥24
- GLM-5-Turbo ¥5 / ¥22
- GLM-5 ¥4 / ¥18
- GLM-4.7 ¥2 / ¥8
- GLM-4.5-Air ¥0.8 / ¥2
- GLM-4.7-FlashX ¥0.5 / ¥3
- GLM-4.7-Flash Free
- GLM-4-Plus ¥5 / ¥5
- GLM-4-Air-250414 ¥0.5 / ¥0.5
- GLM-4-AirX ¥10 / ¥10
- GLM-4-Long ¥1 / ¥1
- GLM-4-Assistant ¥5 / ¥5
- GLM-Z1-Air ¥0.5 / ¥0.5
- GLM-Z1-AirX ¥5 / ¥5
- GLM-Z1-FlashX ¥0.1 / ¥0.1
- GLM-4-FlashX-250414 ¥0.1 / ¥0.1
- GLM-4-Flash-250414 Free
- GLM-Z1-Flash Free
- GLM-OCR ¥0.2 / ¥0.2
- GLM-5V-Turbo ¥5 / ¥22
- GLM-4.6V ¥1 / ¥3
- GLM-4.6V-FlashX ¥0.15 / ¥1.5
- GLM-4.6V-Flash Free
- GLM-4.5V ¥2 / ¥6
- GLM-4V-Plus-0111 ¥4 / ¥4
- GLM-4V-Flash Free
- GLM-4.1V-Thinking-FlashX ¥2 / ¥2
- GLM-4.1V-Thinking-Flash Free
- GLM-Image ¥0.1 /call
- CogVideoX-3 ¥1 /call
- CogView-4 ¥0.06 /call
- CogVideoX-2 ¥0.5 /call
- ViduQ1-Text ¥2.5 /call
- ViduQ1-Image ¥2.5 /call
- ViduQ1-Start-End ¥2.5 /call
- Vidu2-Image ¥1.25 /call
- Vidu2-Start-End ¥1.25 /call
- Vidu2-Reference ¥2.5 /call
- CogView-3-Flash Free
- CogVideoX-Flash Free
- GLM-TTS Tiered
- GLM-TTS-Clone ¥6 /call
- GLM-ASR-2512 ¥16 / ¥0
- GLM-4-Voice Tiered
- GLM-Realtime-Flash ¥0.18 /min
- GLM-Realtime-Air ¥0.3 /min
- Embedding-3 Tiered
- CodeGeeX-4 Tiered
- Rerank Tiered
FAQ
How much does the Embedding-2 API cost?
Input ¥0.5/1M tokens, output ¥0/1M tokens
How large is the Embedding-2 context window?
8K tokens. Handles long documents, multi-turn conversations and large-scale inputs.
Which input modalities does Embedding-2 support?
Text.
Does Embedding-2 offer Batch API discounts?
Yes. The Batch API gets 50% off — input ¥0.25/1M tokens, output ¥NaN/1M tokens. Suited to non-realtime, asynchronous workloads.
How does Embedding-2 compare with peers on value?
Zhipu BigModel Embedding-2 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 Embedding-2?
Good for: chat systems, customer support, content generation, coding assistance, data analysis.
Does Embedding-2 have a free tier?
Check Zhipu BigModel's official pricing page for the latest free quota, trial policy and tiered pricing. Policies differ by vendor and change over time.