Google model product
Gemini Embedding 001
Gemini Embedding 001 is a Google embedding model for semantic search, retrieval, clustering, and ranking pipelines.
Updated Oct 23, 2026. Default version: Gemini Embedding 001
LLMBoard Embedding Score85.5Gemini Embedding 001
Coverage85%5 benchmark families
Context window2KTokens
Official input price$0.15Google API
Gemini Embedding 001 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemini Embedding 001 Benchmark Results
Benchmark scores for Gemini Embedding 001.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMTEB English v2 Retrieval | Score64.35% | Rank11 | Participants218 | Percentile95.39% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Classification | Score88.88% | Rank13 | Participants261 | Percentile95.38% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Clustering | Score59.39% | Rank13 | Participants221 | Percentile94.55% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Semantic Similarity | Score85.29% | Rank18 | Participants215 | Percentile92.06% | EvidenceA | EvaluatedN/A |
| BenchmarkMTEB English v2 Reranking | Score48.60% | Rank53 | Participants244 | Percentile78.60% | EvidenceA | EvaluatedN/A |
Gemini Embedding 001 Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Gemini Embedding 001 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.15 input, N/A output per 1M
- Official provider
- Lowest third-party
- From $0.15 input, N/A output per 1M via Merge Gateway
- Tracked offerings
- 6
Sort by
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 |
| ProviderTempr 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.
Gemini Embedding 001 Runtime Performance
Provider-specific output speed and catalog latency for Gemini Embedding 001. Runtime does not affect the capability score.
No runtime data
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.
Gemini Embedding 001 Specifications
Technical details for the model's default version.
- Version
- Gemini Embedding 001
- Released
- May 20, 2025
- Knowledge cutoff
- May 1, 2025
- Parameters
- N/A
- Context window
- 2K
- Max output
- 1
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Unspecified
Gemini Embedding 001 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGemini Embedding 001 | Released | LLMBoard85.49 | ParametersN/A | Context2K | Max output1 | Open weightsNo | LicenseUnspecified |
Models similar to Gemini Embedding 001
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
text-embedding-005
GOGoogle
text-embedding-004
GOGoogle
embeddinggemma-300m
GOGoogle
text-multilingual-embedding-002
GOGoogle
embeddinggemma-2
GOGoogle
siglip-large-patch16-256
What is Gemini Embedding 001?
Key information about Gemini Embedding 001 and its available data.
Gemini Embedding 001 is an embedding model from Google designed for use in semantic search, retrieval, clustering, and ranking pipelines.
Data as of 2026-10-22.
FAQ
Common questions about Gemini Embedding 001.
When was Gemini Embedding 001 released?
Gemini Embedding 001's default version was released on May 20, 2025.
How much does Gemini Embedding 001 cost?
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.
Who created Gemini Embedding 001?
Gemini Embedding 001 was created by Google.
What is the context window for Gemini Embedding 001?
The default version has a 2K token context window.
Is Gemini Embedding 001 open weight?
No. The default version is not marked as having publicly available weights.