Gemini Embedding 2
GoogleReleased Apr 22, 2026
- providers
- 1
- context
- 8.1K
- max out
- 1
- input /M
- $0.20
- cached input /M
- $50.00
- cache write /M
- $50.00
- reasoning /M
- $50.00
About
- knowledge cutoff
- Nov 1, 2025
- open weights
- no
- best for
- extraction
Capabilities
What the model accepts and returns, where a probe through our own gateway proved it.
- streaming
- tools
- json mode
- vision
- audio
Providers
What you pay through us for each provider, and its own list price where that differs.
Google
google-aistudio/gemini-embedding-2- input /M
- $0.20
- output /M
- cache read /M
- $50.00
- cache write /M
- $50.00
Cache read $50.00/M · Cache write $50.00/M
8.1K context1 max out
Not yet. These figures come from the serve test, which measures one request through each provider and folds the results daily.
Served
- served in the last 24 hours
- 100.00%
Across 1 provider, 25 of 25 requests
- Google100.00% · 25 of 25
Rebuilt once a day from the requests we sent, so it is a daily figure and not a live one.
Not yet. These figures come from Artificial Analysis, which the publish pipeline reads once a day.
Integrations
What the model holds, rather than a compatibility grade: nothing here measures how well a particular tool gets on with it, so nothing here scores one.
- answers on
- embeddings
- accepts
- textimageaudiovideopdf
- returns
- text
Use this model
Works with the OpenAI SDK. Point it at our base URL and use this id.
curl https://api.hopscotchlabs.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google-aistudio/gemini-embedding-2",
"messages": [{"role": "user", "content": "Hello"}],
"max_tokens": 256
}'