Cloud Inference

Embed and Search in One API Call

Qdrant Cloud runs inference alongside your vector search, so you can simplify your data pipeline.

Start Free Explore the Docs

Qdrant Cloud console showing the Inference tab with dense text embedding models

Why It Matters

Pick the Right Embedding Model, Or Bring Your Own

Use the embedding model that fits your use case.

Start at no cost: BM25 and a dense model like all-MiniLM-L6-v2 are free to use, including on free-tier clusters. On paid clusters, models like mxbai and SPLADE run on metered tokens with a monthly free allowance of up to 5 million tokens per model.

Choose from supported hosted models or bring your own API key for an external provider. Send text or images; Qdrant embeds and searches in one call.

Follow the embedding model migration guide

Embed without leaving your cluster

Inference runs inside your Qdrant Cloud cluster's network, so every upsert and query stays on one path, with no external hops, no extra egress, and fewer moving parts to maintain.

Text, image, and sparse vector models included

Managed Cloud gives you access to multimodal embeddings, plus sparse vector support for BM25-style retrieval, all callable through the same API as your database.

Bring your own model or provider

Point the client at an externally hosted model, or run your own client-side inference locally using Qdrant's FastEmbed library. You're never locked to a fixed model catalog.

Swap and test without rebuilding

Retrieval performance and domain specificity both depend on the embedding model you choose. Swapping models on Managed Cloud makes migration significantly easier.

Your application sending text and images to an embedding model inside a Qdrant Cloud cluster, writing to collections A, B, and C

One call from query to result.
Send raw text, image or multivectors, get ranked results back. Your application code handles one request type, covering both vectorization and retrieval in a single operation.
Run hybrid search at no inference cost.
Pair a free dense model like all-MiniLM-L6-v2 with BM25; free models carry no token charges and are available even on free-tier clusters. SPLADE and other larger models are metered. Sparse and dense embeddings run together, so keyword-precision and semantic recall are available in the same query through the same managed endpoint. Cluster resources bill as usual.

Read About Inference

Cloud Inference Enabled Automatically

Managed deployments on Qdrant Cloud have Cloud Inference enabled by default at no extra cost. Name the model in your upsert or query call and Qdrant embeds it in-cluster.

Pass your content as an Inference Object

In your upsert or query, replace the pre-computed vector with an Inference Object: the input, such as text or an image, plus the model to use. Qdrant embeds in-cluster on the same request, storing the vector when you write and matching against it when you search.

Keep one integration surface for external models

Point the call at OpenAI, Cohere, Jina AI, or OpenRouter and Qdrant Cloud proxies the request with your provider key, then stores or searches the result in the same operation. Your application uses the Qdrant client, with no provider SDKs to maintain.

Managed Cloud

Hybrid Cloud

Private Cloud/OSS

Qdrant-hosted embedding models

Available: automatically enabled on new clusters

Not available

In-cluster proxy to externally hosted models

Available

Not available

In-cluster BM25

Available

Talk Through Sizing With Our Team

FAQs

Which models are available through Cloud Inference on Managed Cloud?

Managed Cloud includes dense text models, multimodal (text and image) models, multi-vector models, and sparse (BM25) models on the free tier, with additional larger models on paid clusters. External providers (OpenAI, Cohere, Jina AI, OpenRouter) are supported with your own API key. For the current list, see the Inference tab in the Console.

Can I use my own fine-tuned embedding model with Managed Cloud?

Yes. You can point the client at an externally hosted model, or generate vectors yourself and upsert them as raw vectors. This client-side approach runs entirely in your application, for example with Qdrant's FastEmbed library, and is separate from Cloud Inference. To add a model to our hosted lineup, request it at support.qdrant.io.

Is Cloud Inference available on Hybrid Cloud or self-hosted deployments?

Cloud Inference is a Managed Cloud feature. Hybrid Cloud and self-hosted deployments use client-side inference or in-cluster BM25, as well as any external embedding provider. See the inference documentation.

Which regions is Cloud Inference available in?

Inference runs in the EU for clusters in EU regions and in the US for clusters in all other regions. Free models are hosted in the US region but can be called from any region.

What are the pricing and billing details for Cloud Inference?

Inference is billed per token at a fixed, region-independent price that depends on the model. Each model's price and your current usage appear in the Inference tab of the cluster detail page in the Cloud Console. Free models carry no token charges, and paid Qdrant Cloud users receive a monthly free allowance of up to 5 million tokens per model. For questions specific to your usage volume, contact Qdrant.

Embed and Search in One API Call

Pick the Right Embedding Model, Or Bring Your Own

Embed without leaving your cluster

Text, image, and sparse vector models included

Bring your own model or provider

Swap and test without rebuilding

Need a Model We Don't Host Yet?

Inference Runs Inside Your Cluster

One call from query to result.

Run hybrid search at no inference cost.

From Raw Content to Search Results in Three Steps