Google model product
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Updated Aug 17, 2026. Default version: Gemini Embedding 001
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Gemini Embedding 001.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMTEB(eng, v2) Classification | Score88.9% | Rank11 | Participants253 | PercentileN/A | EvidenceA | Evaluated |
| BenchmarkMTEB(eng, v2) Retrieval | Score64.4% | Rank11 | Participants208 | PercentileN/A | EvidenceA | Evaluated |
| BenchmarkMTEB(eng, v2) Clustering | Score59.4% | Rank13 | Participants213 | PercentileN/A | EvidenceA | Evaluated |
| BenchmarkMTEB(eng, v2) Semantic Similarity | Score85.3% | Rank18 | Participants207 | PercentileN/A | EvidenceA | Evaluated |
| BenchmarkMTEB(eng, v2) Reranking | Score48.6% | Rank51 | Participants237 | PercentileN/A | EvidenceA | Evaluated |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Official vendor API pricing appears first, followed by individual provider offers.
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderVertex | Provider model IDgemini-embedding-001 | Regionglobal | Input / 1M$0.15 | Output / 1MN/A | Context2K | Updated |
| ProviderGoogle | Provider model IDgemini-embedding-001 | Regionglobal | Input / 1M$0.15 | Output / 1MN/A | Context2K | Updated |
| ProviderMerge Gateway | Provider model IDgoogle/gemini-embedding-001 | Regionglobal | Input / 1M$0.15 | Output / 1MN/A | Context2K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for Gemini Embedding 001. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGemini Embedding 001 | Released | LLMBoard85.4 | ParametersN/A | Context2K | Max output1 | Open weightsNo | LicenseUnspecified |
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about Gemini Embedding 001 and its available data.
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Data as of 2026-08-17.
Common questions about Gemini Embedding 001.
Gemini Embedding 001's default version was released on May 20, 2025.
Gemini Embedding 001's official API price is $0.15 per million input tokens and N/A per million output tokens via Google. The lowest tracked third-party offer starts at $0.15 input and N/A output via Merge Gateway.
Gemini Embedding 001 was created by Google.
The default version has a 2K token context window.
No. The default version is not marked as having publicly available weights.
5 provider offerings are linked to the default version.
Nearby ranked alternatives include Seed1.6-embedding, LGAI-Embedding-Preview, F2LLM-v2-14B.