> ## Documentation Index
> Fetch the complete documentation index at: https://docs.neuraltrust.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Embeddings

> Call POST /{consumer}/v1/embeddings with an OpenAI-shaped body. TrustGate routes only to registries that can embed.

Clients send the same OpenAI embeddings body they would send to OpenAI. Auth and the
consumer slug are the same as [chat](/trustgate/getting-started/quickstart#call-from-your-application).

```bash theme={null}
curl -X POST "https://<gateway-host>/<consumer-slug>/v1/embeddings" \
  -H "X-AG-API-Key: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": ["Hello from TrustGate"]
  }'
```

On a Private data plane, add `X-AG-Gateway-Slug` as in the chat snippets.

## Providers

| Registry                       | Upstream                                                                                                                         |
| ------------------------------ | -------------------------------------------------------------------------------------------------------------------------------- |
| **OpenAI**                     | `{base_url}/embeddings` (default `https://api.openai.com/v1/embeddings`)                                                         |
| **Azure OpenAI**               | `{endpoint}/openai/deployments/{model}/embeddings?api-version=…`                                                                 |
| **Mistral**                    | `https://api.mistral.ai/v1/embeddings` (chat host unchanged)                                                                     |
| **Custom / OpenAI-compatible** | `{base_url}/embeddings`                                                                                                          |
| **Cohere**                     | Same OpenAI body, adapted to Cohere `/v2/embed`                                                                                  |
| **Vertex AI**                  | Gemini `:embedContent` (one input) or `:batchEmbedContents` (many)                                                               |
| **Amazon Bedrock**             | Titan **embed** only (`InvokeModel` with `{inputText}`). Model IDs that contain `titan-embed`, including `eu.` / `us.` prefixes. |

Anthropic, Gemini (AI Studio), Bedrock Claude / Nova / Titan **text**, and other chat-only
providers do not embed. They are left out of the candidate pool.

Bedrock rejects a non–Titan-embed model with a 400. Vertex embeddings ignore the chat
`provider_options.action` — they always call the embed endpoints.

## Routing

1. The consumer's registries are filtered to those that advertise embeddings.
2. [Model resolution](/trustgate/routing/model-resolution) and
   [load balancing](/trustgate/routing/load-balancing) run on that pool.
3. Pinning a registry that cannot embed is a **400**, not a failover.
4. An empty capable pool is a **503**.

Attach at least one embeddings-capable registry to the consumer. A mixed chat + embeddings
pool is fine: chat still uses every chat-capable member; embeddings skip the rest.

## Related

* [Registries](/trustgate/concepts/registries)
* [Consumers](/trustgate/concepts/consumers) — Connect tab
* [Rerank](/trustgate/routing/rerank)
* [Files](/trustgate/routing/files)
* [Models](/trustgate/routing/models)
* [Quickstart](/trustgate/getting-started/quickstart)