[Google](/ai-gateway/models/labs/google)

# Text Multilingual Embedding 002

Text Multilingual Embedding 002 is an 18-language text embedding model achieving a 56.2% average score on the Massive Information Retrieval Across Languages (MIRACL) benchmark, designed for cross-lingual semantic search and retrieval across diverse language corpora. Your use is subject to Google's [Terms](https://policies.google.com/terms/generative-ai) & [Privacy](https://policies.google.com/privacy) Policies.

[Use with AI Gateway](https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai%3Futm_source%3Dgateway-model-page%26utm_campaign%3Dai-gateway-models&title=Get+Started+with+Vercel+AI+Gateway) [View docs](https://vercel.com/docs/ai-gateway)

```
1import { embed } from 'ai';
2

3const result = await embed({
4  model: 'google/text-multilingual-embedding-002',
5  value: 'Sunny day at the beach',
6})
```

[Read docs](https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk)

[Overview](/ai-gateway/models/text-multilingual-embedding-002) [About](/ai-gateway/models/text-multilingual-embedding-002/about) [Providers](/ai-gateway/models/text-multilingual-embedding-002/providers) [Similar](/ai-gateway/models/text-multilingual-embedding-002/similar) [FAQ](/ai-gateway/models/text-multilingual-embedding-002/faq)

## [Copy link to heading](#providers)Providers

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the [docs](/docs/ai-gateway/provider-options) for more info. Using a provider means you agree to their terms, listed under Legal.

| Provider |
| --- |

| Context | Input | Capabilities | ZDR | No Training | Release Date |  |
| --- | --- | --- | --- | --- | --- | --- |

| ![vertex logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fvertex%2520ai.png&w=48&q=75) [Google Vertex AI](/ai-gateway/models/providers/vertex) Legal:[Terms](https://cloud.google.com/terms/service-terms)•[Privacy](https://cloud.google.com/privacy) |  | $0.03/M |  |  |  | 03/01/2024 |  |
| --- | --- | --- | --- | --- | --- | --- | --- |

## [Copy link to heading](#more-models-by-google)More models by Google

All

Text

Code

Video Input

| Model |
| --- |

| Context | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | Providers | ZDR | No Training | Release Date |  |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |

| ![google logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgoogle.png&w=48&q=75) [google/gemini-3.7-flash](/ai-gateway/models/gemini-3.7-flash) | 1M | 1.9s | 558tps | $1.50/M$0.75/M | $7.50/M$3.75/M | Read:$0.15/M$0.07/M Write:— | — | +3 | ![google logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgoogle.png&w=48&q=75) ![vertex logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fvertex%2520ai.png&w=48&q=75) |  |  | 08/13/2026 |  |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| ![google logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgoogle.png&w=48&q=75) [google/gemini-3.5-flash-lite](/ai-gateway/models/gemini-3.5-flash-lite) | 1M | 0.5s | 308tps | $0.30/M | $2.50/M | Read:$0.03/M Write:— | $14/K+1 more \+ input costs | +3 | ![google logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgoogle.png&w=48&q=75) ![vertex logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fvertex%2520ai.png&w=48&q=75) |  |  | 07/21/2026 |  |
| ![google logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgoogle.png&w=48&q=75) [google/gemini-3.5-flash](/ai-gateway/models/gemini-3.5-flash) | 1M | 3.6s | 183tps | $1.50/M | $9/M | Read:$0.15/M Write:— | $14/K+1 more \+ input costs | +3 | ![google logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgoogle.png&w=48&q=75) ![vertex logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fvertex%2520ai.png&w=48&q=75) |  |  | 05/19/2026 |  |
| ![google logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgoogle.png&w=48&q=75) [google/gemini-3.1-flash-lite](/ai-gateway/models/gemini-3.1-flash-lite) | 1M | 0.6s | 229tps | $0.25/M | $1.50/M | Read:$0.03/M Write:— | $14/K+1 more \+ input costs | +3 | ![google logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgoogle.png&w=48&q=75) ![vertex logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fvertex%2520ai.png&w=48&q=75) |  |  | 05/07/2026 |  |
| ![google logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgoogle.png&w=48&q=75) [google/gemini\-3-flash](/ai-gateway/models/gemini-3-flash) | 1M | 0.6s | 197tps | $0.50/M+1 more | $3/M+1 more | Read: $0.05/M+1 more Write: — | $14/K+1 more \+ input costs | +3 | ![google logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgoogle.png&w=48&q=75) ![vertex logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fvertex%2520ai.png&w=48&q=75) |  |  | 12/17/2025 |  |
| ![google logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgoogle.png&w=48&q=75) [google/gemini-2.5-flash-lite](/ai-gateway/models/gemini-2.5-flash-lite) | 1M | 0.2s | 392tps | $0.10/M | $0.40/M | Read:$0.01/M Write:— | $35/K+1 more \+ input costs | +3 | ![google logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgoogle.png&w=48&q=75) ![vertex logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fvertex%2520ai.png&w=48&q=75) |  |  | 06/17/2025 |  |

## [Copy link to heading](#about-text-multilingual-embedding-002)About Text Multilingual Embedding 002

Text-multilingual-embedding-002 is Google's embedding model purpose-built for multilingual natural language processing (NLP) applications. Released alongside text-embedding-005 at Google Cloud Next '24, it uses the same Gecko architecture but targets cross-lingual coverage rather than maximum English-language benchmark performance. Its primary evaluation benchmark is MIRACL (Massive Information Retrieval Across Languages), covering 18 languages, where it achieves a 56.2% average score.

The practical value lies in vector space alignment across languages. Rather than running separate monolingual models for each language in your corpus, text-multilingual-embedding-002 embeds content from all 18 supported languages into a shared semantic space. A query submitted in one language can surface relevant documents written in any other supported language, without a translation step. For global products, international content platforms, or multilingual knowledge bases, this shared embedding space eliminates the complexity of language detection and routing.

Like its English-only sibling, text-multilingual-embedding-002 supports dynamic embedding sizes through Matryoshka Representation Learning (MRL). You can choose smaller dimension outputs to reduce vector storage and compute costs, with a minor quality tradeoff. This flexibility matters for multilingual applications where the corpus may be significantly larger than a monolingual equivalent.

## [Copy link to heading](#what-to-consider-when-choosing-a-provider)What To Consider When Choosing a Provider

- Configuration: For multilingual retrieval applications, this model maps text from all supported languages into the same vector space. That enables cross-lingual queries: for example, a user querying in Japanese can retrieve documents written in Spanish without a query translation layer.
- Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the [documentation](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr) for details.
- Authentication: AI Gateway authenticates requests using an [API key](https://vercel.com/docs/ai-gateway/authentication-and-byok#api-key-authentication) or [OIDC token](https://vercel.com/docs/ai-gateway/authentication-and-byok#oidc-token-authentication). You do not need to manage provider credentials directly.

## [Copy link to heading](#when-to-use-text-multilingual-embedding-002)When to Use Text Multilingual Embedding 002

### Best for

- Multilingual semantic search: Applications serving users who query in different languages than the indexed content
- Cross-lingual document retrieval: Knowledge base search across international content corpora
- Global customer support: Systems where user questions and knowledge base articles span multiple languages
- Multilingual clustering and classification: Tasks that need consistent semantic representations across languages
- International content platforms: E-commerce or media indexing product descriptions or articles in multiple languages

### Consider alternatives when

- English-only corpus: Your corpus and users are exclusively English-language (consider `google/text-embedding-005` for higher MTEB scores)
- Unsupported language needed: You require a language not covered by the 18-language MIRACL benchmark, verify support in the Vertex AI documentation
- Peak English retrieval quality: Multilingual support is not required and maximum English performance is the primary criterion

## [Copy link to heading](#conclusion)Conclusion

Text-multilingual-embedding-002 solves the core infrastructure challenge of multilingual retrieval: maintaining a single vector index that serves queries and documents across 18 languages without translation layers or per-language model management. For global applications where your user base and content corpus span multiple languages, it provides the embedding foundation that makes cross-lingual semantic search tractable.