---
title: "Morph + Weaviate"
description: "Morph serves code and text embedding models behind an OpenAI-compatible API. Weaviate integrates with Morph's embedding endpoint so you can vectorize and search data using Morph-hosted models directly from your Weaviate instance."
url: https://docs.weaviate.io/weaviate/model-providers/morph
---

# Morph + Weaviate

[Morph](https://morphllm.com/) serves code and text embedding models behind an OpenAI-compatible API. Weaviate integrates with Morph's embedding endpoint so you can vectorize and search data using Morph-hosted models directly from your Weaviate instance.

> [!WARNING]
>
> **Morph lists the Embedding API as legacy**
>
> Morph's own documentation labels the Embedding API as legacy and planned for deprecation. Check the current status in [Morph's documentation](https://docs.morphllm.com/) before you build on this integration.

## Integrations with Morph

### Embedding models for vector search

![Embedding integration illustration](https://docs.weaviate.io/assets/images/integration_morph_embedding-58dd962703c490a9834c4f2cbc8107f3.png)

Morph exposes embedding models over an OpenAI-compatible `/v1/embeddings` API at `https://api.morphllm.com`.

[Weaviate integrates with Morph's embedding models](https://docs.weaviate.io/weaviate/model-providers/morph/embeddings) through the `text2vec-morph` vectorizer module. Configure a vector index to use a Morph model and Weaviate generates embeddings for imports, vector searches, and hybrid searches automatically.

[Morph embedding integration page](https://docs.weaviate.io/weaviate/model-providers/morph/embeddings)

## Summary

This integration lets you use Morph's hosted embedding models from Weaviate without managing inference infrastructure yourself.

## Get started

Generate an API key in the [Morph dashboard](https://morphllm.com/), then supply it to Weaviate through the `MORPH_APIKEY` environment variable or the `X-Openai-Api-Key` request header. The header name is shared with the OpenAI integration, because Morph requests are built by the same OpenAI-compatible client inside Weaviate. Then see the embedding integration page:

- [Text Embeddings](https://docs.weaviate.io/weaviate/model-providers/morph/embeddings)