Gemini Embedding 001
Summary
Gemini Embedding 001 is a proprietary language model from Google DeepMind, released on 20 May 2025. It accepts text and generates text, with a 2K-token context window and up to 1 output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.15 per million input tokens and Free per million output tokens (Gemini API), across 3 providers we track.
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Google DeepMind |
|---|---|
| Release date | 20 May 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 2K (2,048 tokens) [models.dev] |
| Max output | 1 tokens [models.dev] |
| Knowledge cutoff | May 2025 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
Gemini Embedding 001 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Gemini API gemini-embedding-001 | $0.15 | Free | – | 2K | models.dev, 18 Nov 2026 |
| Google Vertex AI gemini-embedding-001 | $0.15 | Free | – | 2K | models.dev, 18 Nov 2026 |
| Vercel AI Gateway google/gemini-embedding-001 | – | – | – | 2K | models.dev, 18 Nov 2026 |
Frequently asked questions
What is the context window of Gemini Embedding 001?
Gemini Embedding 001 has a context window of 2,048 tokens (2K) and can generate up to 1 tokens in a single response, according to models.dev.
How much does the Gemini Embedding 001 API cost?
Through Gemini API, Gemini Embedding 001 costs $0.15 per million input tokens and Free per million output tokens. Prices last verified 18 Nov 2026.
Is Gemini Embedding 001 open source?
No. Gemini Embedding 001 is a proprietary model; Google DeepMind has not released its weights. It is available through APIs including Gemini API, Google Vertex AI, Vercel AI Gateway.
When was Gemini Embedding 001 released?
Google DeepMind released Gemini Embedding 001 on 20 May 2025, according to models.dev.
Which providers offer Gemini Embedding 001?
We track Gemini Embedding 001 on 3 providers: Gemini API, Google Vertex AI, Vercel AI Gateway.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Codestral Embed | Mistral AI | 28 May 2025 | 8K | – | – | Closed |
| Cohere Rerank 3.5 | Cohere | 2 Dec 2024 | 4K | – | – | Closed |
| text-embedding-3-large | OpenAI | 25 Jan 2024 | 8K | $0.13 | – | Closed |
| Qwen-VL OCR | Alibaba (Qwen) | 28 Oct 2024 | 34K | $0.07 | $0.16 | Closed |
| solar-pro2 | Upstage | 20 May 2025 | 66K | $0.25 | $0.25 | Closed |
| Qwen-MT Plus | Alibaba (Qwen) | Jan 2025 | 16K | $0.25 | $0.75 | Closed |
Change history
No changes detected since we started tracking this model. We re-check every source daily.