Gemini Embedding 2 API Pricing
Google · released Apr 22, 2026 · 8.2K context · API model ID gemini-embedding-2
Gemini Embedding 2 by Google API pricing: $0.20 per 1M input tokens and free output (provider list price via models.dev, Oct 10, 2026).
Prices
| Price | USD per 1M tokens |
|---|---|
| Input | $0.20 |
| Output | Free |
| Cache read | Not published |
| Cache write | Not published |
| Audio input | $6.50 |
Google's list price for its own API, as compiled by models.dev and checked Oct 10, 2026, 09:00 UTC. Prices on cloud platforms and resellers can differ. Provider documentation
Estimated monthly cost
$60.00
per month
- per day
- $2.00
- per request
- $0.0002
Cannot estimate: a needed price is not published.
Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.
Monthly cost by workload
| Workload | Per month |
|---|---|
| Chatbot1,000 in / 500 out tokens, 10,000 requests a day | $60.00/mo |
| RAG8,000 in / 500 out tokens, 5,000 requests a day | $240.00/mo |
| Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input | $300.00/mo |
Context and capabilities
- Context
- 8,192 tokens
- Max output
- 1 tokens
- Input
- text, image, audio, video, pdf
- Output
- text
- Knowledge cutoff
- November 2025
- Open weights
- No
- Tool calling
- No
- Reasoning
- No
- Structured outputs
- No
Capabilities and limits as listed by models.dev.
Similarly priced models
- Claude Haiku 5.5 · $0.10 in / $0.50 out
- GPT-6 Luna · $0.10 in / $0.50 out
- Qwen3.8 Flash · $0.15 in / $0.47 out
- DeepSeek V4.1 Flash · $0.30 in / $1.20 out
Price history
No price changes since we started tracking on Oct 8, 2026.
Questions
- How much does Gemini Embedding 2 cost per month?
- For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, Gemini Embedding 2 costs about $60.00 per month at Google's list prices ($0.20 per 1M input tokens, free output).
- Does Gemini Embedding 2 support prompt caching?
- No cache read price is published for Gemini Embedding 2.
- How long is Gemini Embedding 2's context window?
- Gemini Embedding 2 accepts up to 8,192 tokens (8.2K) of context and returns up to 1 tokens per response.