Google: Gemini Embedding 2 (batch)
google/gemini-embedding-2:batch
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenRouter's catalog describes google/gemini-embedding-2:batch as a Google embedding endpoint under the canonical ID google/gemini-embedding-2. The catalog lists text, image, file, audio, and video inputs producing embeddings, while its description more narrowly says text and images can share one vector space for semantic search and retrieval-augmented generation. It also lists a context length of 8,192. No independent model card or measured benchmark results were included in this source pack.[1]
Strengths
- The catalog presents one embedding-producing endpoint with text, image, file, audio, and video listed as input modalities.[1]
- The catalog description reports that text and images are mapped into a shared vector space, enabling semantic comparisons across those two modalities.[1]
- A context length of 8,192 is listed in the catalog.[1]
Limitations
- The source pack contains only an OpenRouter catalog entry; no independent model card was available, so claims remain catalog-reported.[1]
- No measured benchmark results are supplied; embedding quality, retrieval impact, throughput, latency, and batch behavior should be validated on the intended workload.[1]
- The catalog lists file, audio, and video inputs, but the description only says text and images are currently mapped into a unified space; treat broader modality support and batch-specific limits as unconfirmed.[1]
Where to use it
- Consider for semantic search or RAG over text and image collections; the catalog explicitly associates that shared space with these uses.[1]
- Potentially useful for exploratory indexing of files, audio, or video, but only after confirming that this endpoint handles those inputs as expected.[1]
- Candidate for batch-oriented embedding pipelines if testing confirms the :batch behavior and operational limits.[1]
Sources
- [1] OpenRouter catalog · Google: Gemini Embedding 2 (batch)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports...
Specifications
- Model ID
- google/gemini-embedding-2:batch
- Canonical ID
- google/gemini-embedding-2
- Creator
- Added to OpenRouter
- 20.05.2026
- Context length
- 8,192
- Modality
- text+image+file+audio+video->embeddings
- Input modalities
- text, image, file, audio, video
- Output modalities
- embeddings
- Token pricing
- USD per 1M tokens: in $0.100 / out $0
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | input: file |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | input: audio |
| Video | No measurement | input: video |
| Embeddings | No measurement | output: embeddings |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| 8,192 | $0.100 | $0 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.