Embeddings
MarkdownText embeddings for search, RAG, and clustering.
Full guide
POST
https://api.ailoot.ai/v1/embeddingscurl https://api.ailoot.ai/v1/embeddings \
-H "Authorization: Bearer $AILOOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "nvidia/nemotron-3-embed-1b", "input": ["First document", "Second document"]}' emb = client.embeddings.create(
model="nvidia/nemotron-3-embed-1b",
input=["First document", "Second document"],
)
vectors = [d.embedding for d in emb.data]{
"object": "list",
"data": [
{ "object": "embedding", "index": 0, "embedding": [0.0123, -0.0456, 0.0789, …] },
{ "object": "embedding", "index": 1, "embedding": [-0.0321, 0.0654, 0.0987, …] }
],
"model": "nvidia/nemotron-3-embed-1b",
"usage": { "prompt_tokens": 8, "total_tokens": 8 }
}Authentication
- Authorizationheaderrequired
The key in the format
Bearer sk-…. The following headers also work:x-api-keyorx-goog-api-key.
Request body
- modelstringrequired
Embedding model:
nvidia/nemotron-3-embed-1b,nvidia/llama-nemotron-embed-vl-1b-v2. - inputstring | arrayrequired
A string or an array of strings. Each input is limited by the model's context window (4096 tokens for NVIDIA models).
- encoding_formatstringoptional
float(default) orbase64— if supported by the model.
Response
- data[].embeddingarray
A numeric vector for each input, in the same order.
- usageobject
Number of input tokens. Embedding output is not billed.
Still have questions? Send your Request ID and a description — we'll help you troubleshoot.Contact support