API: Embeddings

OpenAI-compatible embeddings endpoint of the Kasimir Public API for 1024-dimensional vector embeddings.

The embeddings endpoint converts text into vectors that you can use for semantic search, clustering, classification or your own RAG applications. It is compatible with the OpenAI Embeddings API: you can use the official OpenAI SDK (or any OpenAI-compatible client) unchanged and only point base_url and api_key at Kasimir. Your company’s model approvals and budget apply.

Endpoint

Authentication

Every call is authenticated with a company API key passed in the Authorization: Bearer <key> header.

• Owners and admins create keys under Administration → Access.

• A key starts with kasi_ and is shown in full only once at creation.

• New keys have the scopes chat:read and chat:write by default. Embeddings require chat:write.

• Revoked keys are rejected with 401.

Request

Headers

Body parameters

Response

The response follows the OpenAI embeddings schema. The model field contains the Kasimir slug.

Each element in data:

Examples

curl — single text

curl https://kasimir.ai/api/v1/embeddings \
  -H "Authorization: Bearer kasi_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jina-embeddings-v3",
    "input": "The GDPR governs the handling of personal data."
  }'

curl — batch (multiple texts)

curl https://kasimir.ai/api/v1/embeddings \
  -H "Authorization: Bearer kasi_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jina-embeddings-v3",
    "input": [
      "First paragraph to embed.",
      "Second paragraph to embed."
    ]
  }'

OpenAI Python SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://kasimir.ai/api/v1",
    api_key="kasi_YOUR_API_KEY",
)

resp = client.embeddings.create(
    model="jina-embeddings-v3",
    input="The GDPR governs the handling of personal data.",
)

vector = resp.data[0].embedding
print(len(vector))   # 1024
print(resp.usage.prompt_tokens)

Batch with the Python SDK

texts = [
    "First paragraph to embed.",
    "Second paragraph to embed.",
]

resp = client.embeddings.create(model="jina-embeddings-v3", input=texts)

for item in resp.data:
    print(item.index, len(item.embedding))

Example response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0123, -0.0456, 0.0789, "...1021 more values..."]
    }
  ],
  "model": "jina-embeddings-v3",
  "usage": {
    "prompt_tokens": 12,
    "total_tokens": 12
  }
}

Listing models

To discover which slugs are entitled for your workspace, use the models endpoint. It returns both chat and embedding models (filtered by your company’s approvals and EU setting):

curl https://kasimir.ai/api/v1/models \
  -H "Authorization: Bearer kasi_YOUR_API_KEY"

client.models.list()

Errors

Errors are returned in the OpenAI error format so that standard SDKs handle them normally:

{
  "error": {
    "message": "Missing scope: chat:write",
    "type": "permission_error",
    "code": null
  }
}

The HTTP status code determines the type field:

Governance & billing

• Model approval: the same rules apply as in the app’s model picker – only active embedding models enabled for your company.

• EU approval: models outside the EU are rejected with 403 unless your company has explicitly enabled them. The default model is EU-hosted.

• Usage: every successful call is recorded with tokens and cost in euros and counts towards the monthly budget.