Gemini Embedding
google/gemini-embeddingHigh-recall embeddings backed by Gemini's multilingual foundation.
Model overview
Context window
8K
tokens
Input price
—
quoted on request
Output price
—
quoted on request
Weekly volume
—
tokens / week
Open weights
No
API only
Capabilities
1
of 11 tags
Description
Gemini Embedding is an embeddings model from Google. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. Google’s stated focus is frontier multimodality at planetary scale. The weights are not published, so it is API-only.
Capabilities
- Batch
- Accepts offline batch jobs, which are processed asynchronously at a reduced rate.
Strengths & weaknesses
Strengths
- Excellent multilingual recall
- Stable, versioned releases
- Batch pricing
Weaknesses
- 8K context per input
- Text-only
Pricing
| Rate | Price | Unit |
|---|---|---|
| Input | — quoted on request | — |
| Output | — quoted on request | — |
Batch jobs are supported and settle at a reduced rate against the same unit. This model is not provisioned yet; the rate is quoted on request.
Context window
8Ktokens
covers prompt and response together, so a long input leaves less room for the answer.
Supported features
| Feature | Support |
|---|---|
| Tool calling | Not supported |
| JSON mode | Not supported |
| Streaming | Not supported |
| Vision input | Not supported |
| Audio input | Not supported |
| Long context | Not supported |
| Open weights | Not supported |
| Reasoning | Not supported |
| Fine-tunable | Not supported |
| Batch | Supported |
| Caching | Not supported |
Example use cases
Semantic search
Classification
Clustering
Comparison
Compare against anything →| Attribute | Gemini Embedding | Embed v4 | Qwen3 Embedding |
|---|---|---|---|
| Context window | 8K | 128K | 32K |
| Input price | R0.00 | R0.00 | R0.00 |
| Output price | — not charged | — not charged | — not charged |
| Tool calling | Not supported | Not supported | Not supported |
| JSON mode | Not supported | Not supported | Not supported |
| Vision input | Not supported | Supported | Not supported |
| Open weights | Not supported | Not supported | Not supported |
| Prompt caching | Not supported | Not supported | Not supported |
Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.
Provider information
View Google →Google · Mountain View, United States · est. 1998 (DeepMind model era from 2023)
Google DeepMind's Gemini line is natively multimodal (text, vision and audio in one system) backed by custom TPU infrastructure nobody else can match. Veo and Imagen lead generative media, and Gemini's long-context engineering set the 1M-token standard the industry chased.
Recent releases
Documentation
Frequently asked questions
Input is billed at R0.00 per 1M tokens, and there is no separate output charge. Batch jobs settle at a reduced rate against the same unit. Every figure on this page is an illustrative placeholder.
No. Gemini Embedding is served through its provider's API only; the weights are not published, so self-hosting is not an option.
Prompt and response share one window: Gemini Embedding accepts up to 8K tokens in total, so a long input leaves less room for the answer. The median across embeddings models is 32K. Recall is strongest well inside the limit. Test at your real prompt depth before relying on the ceiling.
Embed v4 is the closest neighbour in the catalogue, with 128K of context at R0.00 per 1M tokens in. Put both in a comparison before wiring a fallback chain, so the trade-off is a decision rather than a default.