Voyage AI

Add a Voyage AI API key under Settings, Model Providers and call Voyage embedding models through the LangWatch AI Gateway.

Add the credential

Open Settings > Model Providers, click Add Model Provider and select Voyage AI. Give the row a name, pick the organization, team or project it belongs to, and fill in:

Field	Value
VOYAGE_API_KEY	Your Voyage AI API key.

Save the row. Every virtual key whose scope can see the row can now dispatch to it, unless the key restricts its providers. See Virtual keys.

The Voyage AI row: name, scope, VOYAGE_API_KEY and the routing handle voyage.

Model names

Write the Voyage model id, for example voyage-3.5 or voyage/voyage-3.5. The gateway strips the voyage/ prefix before it calls Voyage.

Send a request

curl https://gateway.langwatch.ai/v1/embeddings \
  -H "Authorization: Bearer $LANGWATCH_VIRTUAL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "voyage-3.5",
    "input": ["The quick brown fox"]
  }'

The gateway sends the request to https://api.voyageai.com/v1/embeddings and returns the OpenAI embeddings shape.

Endpoints

Voyage AI serves POST /v1/embeddings only. Any other request to a Voyage row is rejected with the message voyage credentials only accept embedding requests.