Build next-gen apps with gemini-embedding-001
Pricing
TokenLab Price
Input $0.075 / Output $0.00
Discount: 50%
| Official PricePer 1M Tokens | TokenLab PricePer 1M Tokens | Discount | |
|---|---|---|---|
| Input | $0.15 | $0.075 | 50% |
| Output | $0.00 | $0.00 | - |
One-click test
Sign in once and Web Agent keeps this model, prompt, and request preset for you.
Test gemini-embedding-001 in Web Agent. Run a minimal embedding request at /v1/embeddings, then show request body and response shape.
API workbench
The default route for production. The code sample below uses this endpoint with the format you pick.
curl "https://api.tokenlab.sh/v1beta/models/gemini-embedding-001:generateContent" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: sk-xxx" \
-d '{
"contents": [
{"role": "user", "parts": [{"text": "Hello!"}]}
]
}'Use cases
Semantic search
Build vector representations for search, recommendations, clustering, and RAG.
Side-by-side test
Compare real response quality, latency, and price for production defaults.
Prompt examples
Embed five product FAQ snippets and explain the response shape.
Send the smallest possible request and walk me through every response field.
Compare this model with a cheaper one in the same category — when is each worth it?
Cost Calculator
FAQ
How much does gemini-embedding-001 cost?
On TokenLab, gemini-embedding-001 costs $0.075 per 1M input tokens and $0.00 per 1M output tokens. Cache and per-request prices show in the pricing table when they apply.
How do I call the gemini-embedding-001 API?
Get a TokenLab API key, then send your request to https://api.tokenlab.sh/v1/embeddings. The API workbench above has a recommended endpoint and copy-ready code.
Which endpoint should gemini-embedding-001 use?
Use https://api.tokenlab.sh/v1/embeddings as the default for gemini-embedding-001. If a provider-native format is supported, the API workbench shows that endpoint too.
Can I test gemini-embedding-001 before integrating it?
Yes. Try in Web Agent opens a ready test for gemini-embedding-001 and keeps your prompt after sign-in, so you don’t lose context.
