Conversation / Quote
Gemini Embedding 2 API Price
Google · gemini-embedding-2
| Billing | USD · 1M tokens |
|---|---|
| Modalities | Text / Image / Video / Audio |
| Deep Thinking | — |
| Batch API | 50% off (input $0.1 / output $NaN) |
| Verified Date | 2026-10-10 |
| Official pricing page | ai.google.dev/gemini-api/docs/pricing ↗ |
Source text: the note below is the model's official text, kept in its original Chinese and not translated.
First multimodal embedding model (text/images/video/audio/PDFs). Batch: text $0.10, image $0.225 ($0.00006/image), audio $3.25 ($0.00008/sec), video $6.00 ($0.000395/frame).
Report a pricing issue
Found inaccurate pricing or model information? We will review it.
Pricing Tiers
| Tier | Price | Description |
|---|---|---|
| text input | in $0.2 /1M tokens | — |
| image input | in $0.45 /1M tokens | $0.00012 per image |
| audio input | in $6.5 /1M tokens | $0.00016 per second |
| video input | in $12 /1M tokens | $0.00079 per frame |
Google Related Models
- Gemini 3.8 Flash $0.75 / $3.75
- Gemini 3.7 Flash $0.75 / $3.75
- Gemini 3.6 Flash $0.75 / $3.75
- Gemini 3.6 Flash-Tiered $0.75 / $3.75
- Gemini 3.5 Flash $1.5 / $9
- Gemini 3.5 Flash-Lite $0.3 / $2.5
- Gemini 3.1 Flash-Lite $0.25 / $1.5
- Gemini 3.1 Pro Preview $2 / $12
- Gemini 3 Pro Preview(Legacy) $2 / $12
- Gemini 3 Flash(Legacy) $0.5 / $3
- Gemini 2.5 Pro $1.25 / $10
- Gemini 2.5 Flash $0.3 / $2.5
- Gemini 2.5 Flash-Lite $0.1 / $0.4
- Gemini 3.8 Live $0.75 / $4.5
- Gemini 3.5 Live Translate $3.5 / $21
- Gemini 3.1 Flash Image $0.5 / $60
- Gemini 3.1 Flash Lite Image $0.25 / $30
- Gemini 3 Pro Image $2 / $120
- Nano Banana Pro (Gemini 3 Pro Image, Preview channel) $2 / $120
- Veo 3.1 $0.4 /sec
- Veo 3.1 Fast $0.1 /sec
- Veo 3.1 Lite $0.05 /sec
- Veo 2.0(Discontinued) $0.35 /sec
- Veo 3.0(Discontinued) $0.4 /sec
- Veo 3.0 Fast(Discontinued) $0.15 /sec
- Gemini Omni Flash $1.5 / $17.5
- Gemini 3.8 Flash TTS $0.5 / $9
- Gemini 3.8 Flash-Lite TTS $0.5 / $6
- Gemini 3.1 Flash TTS Preview $1 / $20
- Gemini 2.5 Flash Preview TTS $0.5 / $10
- Gemini 2.5 Pro Preview TTS $1 / $20
- Gemini 3.5 Transcribe $2 / $12
- Gemini 3.5 Transcribe Live $3.5 / $21
- Lyria 3.5 $0.08 /call
- Lyria 3 Clip Preview $0.04 /call
- Lyria 3 Pro Preview $0.08 /call
- Gemini 3.8 Live Extended Thinking $0.75 / $4.5
- Gemini 3.1 Flash Live Preview $0.75 / $4.5
- Gemini Omni Flash Preview $1.5 / $17.5
- Gemini 3.1 Pro Preview (Custom Tools) $2 / $12
- Gemini Nano Banana 2.1 $1.5 / $30
- Gemini 3 Flash Preview $0.5 / $3
- Gemini 2.5 Flash Native Audio $0.5 / $12
- Gemini 2.5 Flash Image $0.3 / $30
- Gemini Robotics ER 2 Preview $1 / $5
- Gemini Robotics ER 2 Streaming Preview $1 / $5
FAQ
How much does the Gemini Embedding 2 API cost?
Input $0.2/1M tokens, output $0/1M tokens
Which input modalities does Gemini Embedding 2 support?
Text / Image / Video / Audio.
Does Gemini Embedding 2 offer Batch API discounts?
Yes. The Batch API gets 50% off — input $0.1/1M tokens, output $NaN/1M tokens. Suited to non-realtime, asynchronous workloads.
How does Gemini Embedding 2 compare with peers on value?
Google Gemini 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 Gemini Embedding 2?
Good for: chat systems, customer support, content generation, coding assistance, data analysis.
Does Gemini Embedding 2 have a free tier?
Check Google's official pricing page for the latest free quota, trial policy and tiered pricing. Policies differ by vendor and change over time.