Vectors for search, retrieval, clustering and memory, from text and, with a multimodal model, images, through the OpenAI-compatible embeddings API.
OpenAI-compatible: change the base URL and key, pick a model by id.
Semantic search, retrieval for agents, deduplication, recommendations.
| Model | Input | Dimensions | State |
|---|---|---|---|
| Qwen3-Embedding 0.6B qwen3-embedding-0.6b | Text | 1024 | Coming online |
| Model | Per 1M tokens |
|---|---|
Qwen3-Embedding 0.6B qwen3-embedding-0.6b | 20 credits |
Charged per token, pro rata, from your credits.
curl https://api.tenzro.xyz/v1/embeddings \
-H "Authorization: Bearer $TENZRO_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "qwen3-embedding-0.6b", "input": ["Tenzro settles in TNZO", "What does Tenzro settle in?"]}'import os
from openai import OpenAI
client = OpenAI(base_url="https://api.tenzro.xyz/v1", api_key=os.environ["TENZRO_API_KEY"])
vectors = client.embeddings.create(
model="qwen3-embedding-0.6b",
input=["Tenzro settles in TNZO", "What does Tenzro settle in?"],
)
print(len(vectors.data[0].embedding))