Gemini Embedding 001

Google's state-of-the-art text embedding model. Default output dimension 3072; supports the `dimensions` parameter to shorten output (recommended: 768, 1536, 3072).

gemini-embedding-001
Embedding modelSTABLEGet StartedView uptime
2,048 context
Released July 14, 2025
Starting at $0.15/M input tokens
Starting at $0.00/M output tokens
Embeddings
No ratings yetSign in to rate

All Providers for Gemini Embedding 001

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

Google AI Studio
Context: 2.0k
Input
$0.15
/M tokens
Cache Read
/M tokens
Output
$0
/M tokens
Get Started
Google Vertex AI
Context: 2.0k
Input
$0.15
/M tokens
Cache Read
/M tokens
Output
$0
/M tokens
Get Started

Frequently asked questions

What is Gemini Embedding 001?

Google's state-of-the-art text embedding model. Default output dimension 3072; supports the `dimensions` parameter to shorten output (recommended: 768, 1536, 3072). You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does Gemini Embedding 001 cost?

Pricing for Gemini Embedding 001 on LLM Gateway starts at $0.15 per million input tokens and $0.00 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of Gemini Embedding 001?

Gemini Embedding 001 supports a context window of up to 2,048 tokens on its largest provider deployment.

Which providers serve Gemini Embedding 001?

Gemini Embedding 001 is served by Google AI Studio, Google Vertex AI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does Gemini Embedding 001 support tool calling and structured outputs?

No. Gemini Embedding 001 does not currently support tool calling or structured JSON outputs through LLM Gateway.

When was Gemini Embedding 001 released?

Gemini Embedding 001 was released on July 14, 2025.