Loading
embed-small
Text embeddings for search, clustering and retrieval; answers the OpenAI-compatible /v1/embeddings endpoint (never chat).
Requests per day this target answered on this deployment, with the cost line.
Domains the signal layer detected on requests that ended here.
Hard stops enforced before scoring.
Examples the similarity strategy matches against.
Pin this target with model="embed-small", or send a candidate list and let the router choose and fall back.
curl https://api.opensmartroute.ai/v1/chat/completions \
-H "Authorization: Bearer $OSR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "embed-small", "messages": [{"role": "user", "content": "Embed these product descriptions for semantic search."}]}'from openai import OpenAI
client = OpenAI(base_url="https://api.opensmartroute.ai/v1", api_key="osr_live_...")
resp = client.chat.completions.create(
model="embed-small", # pin this target, or "auto" to let the router choose
messages=[{"role": "user", "content": "Embed these product descriptions for semantic search."}],
extra_body={"models": ["embed-small", "auto"]}, # fall back to the router's pick if it fails
)
print(resp.model, resp.choices[0].message.content)