Embeddings

POST /v1/embeddings

Request body

Field	Type	Default	Notes
model	string	(the deployment’s model)	Optional; must match if set
input	string | string[]	required	One text or a batch
encoding_format	string	"float"

Example

curl

curl https://<your-deployment>.inference.meshive.ai/v1/embeddings \
  -H "Authorization: Bearer $MESHIVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"input": ["first text", "second text"]}'

Python

resp = client.embeddings.create(model="", input=["first text", "second text"])
print(len(resp.data), len(resp.data[0].embedding))

The response is OpenAI’s embedding list object (data[].embedding, usage).

Rate limits (RPM/TPD) apply as on the other text endpoints — see the overview.