Gemini Embedding
gemini-embedding-001Pricing
List prices at Google AI Studio, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.15 | $0.00 | |
| Batch 50% off | $0.075 | 50% off |
What it costs a month
At Google AI Studio list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$45.00
- RAG over documents2,000 requests a day, 8K in / 0.6K out$72.00
- Coding agent1,000 requests a day, 40K in / 2K out$180
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$180
Where to run it
3 hosts serve Gemini Embedding. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Google AI StudioLab API gemini-embedding-001 | $0.15 / $0.00 Retires 14 May 2028 | gemini-embedding-001 | Retires 14 May 2028 |
Vertex AICloud gemini-embedding-001 | $0.15 / $0.00 Retires 20 May 2028 | gemini-embedding-001 | Retires 20 May 2028 |
Vercel AI GatewayGateway gemini-embedding-001 | $0.15 / $0.00 | gemini-embedding-001 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Embeddings
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Google AI Studio.
Smaller Google models
- 33% less
Other frontier labs
- 13% less
- 33% less
- 87% less
Open-weight picks
- 53% less
- 87% less
- 53% less
- 93% less
Call it
Using Google AI Studio's API.
from google import genai
client = genai.Client() # reads GEMINI_API_KEY
response = client.models.generate_content(model="gemini-embedding-001", contents="Hello")
print(response.text)curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:generateContent" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"contents": [{"parts": [{"text": "Hello"}]}]}'from litellm import completion
response = completion(
model="gemini/gemini-embedding-001",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Gemini Embedding cost?
On Google AI Studio, Gemini Embedding costs $0.15 per million input tokens.
Which APIs offer Gemini Embedding?
Gemini Embedding runs on 3 APIs: Google AI Studio, Vertex AI and Vercel AI Gateway.
What is Gemini Embedding's context window?
2K tokens.
Is Gemini Embedding being retired?
Google AI Studio retires it on 14 May 2028; Vertex AI on 20 May 2028. 1 host keeps serving it.
What are cheaper alternatives to Gemini Embedding?
Models that cost less and keep most of what it can do: Text Embedding 005 on Vertex AI (33% less), Text Embedding 3 Large on OpenAI (13% less), Text Embedding Ada 002 on OpenAI (33% less) and Snowflake Arctic Embed L V2.0 on Snowflake (53% less).
What is Gemini Embedding's API model id?
Use gemini-embedding-001 with Google AI Studio.
Sources
Raw catalog entry for gemini-embedding-001 on Google AI Studio
{
"deprecation_date": "2028-05-14",
"deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations",
"successor_model": "gemini/gemini-embedding-2",
"input_cost_per_token": 1.5e-7,
"litellm_provider": "gemini",
"max_input_tokens": 2048,
"mode": "embedding",
"output_cost_per_token": 0,
"output_vector_size": 3072,
"rpm": 10000,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"tpm": 10000000,
"input_cost_per_token_batches": 7.5e-8
}