Supported Embedding Providers & Models
Qdrant supports all available text and multimodal dense vector embedding models as well as vector embedding services without any limitations.
Code samples
| Embeddings Providers | Description |
|---|---|
| Aleph Alpha | Multilingual embeddings focused on European languages. |
| Bedrock | AWS managed service for foundation models and embeddings. |
| Cohere | Language model embeddings for NLP tasks. |
| Gemini | Google Gemini embeddings for semantic search, classification. |
| Jina AI | Customizable embeddings for neural search. |
| Mistral | Open-source, efficient language model embeddings. |
| MixedBread | Lightweight embeddings for constrained environments. |
| Mixpeek | Managed SDK for video chunking, embedding, and post-processing. |
| Nomic | Embeddings for data visualization. |
| Nvidia | GPU-optimized embeddings from Nvidia. |
| Ollama | Embeddings for conversational AI. |
| OpenAI | Industry-leading embeddings for NLP. |
| Prem AI | Precise language embeddings. |
| Twelve Labs | Multimodal embeddings from Twelve labs. |
| Snowflake | Scalable embeddings for big data. |
| Superlinked | Self-hosted inference engine serving 85+ dense, sparse, and multivector (ColBERT) embedding models from a single endpoint. |
| Upstage | Embeddings for speech and language tasks. |
| Voyage AI | Navigation and spatial understanding embeddings. |